Headed In: Florida trips, water and weather

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, open-world behavior. The description adds valuable context beyond that: the data source (FWC), the statewide deployment count, the returned fields, the closest-first ordering, and a safety caveat against navigation use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the resource and scope, then a dense but useful field list, then intended uses and an exclusion. Every sentence earns its place with no repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and seven optional parameters, the definition does a good job describing return fields and sort order. However, it never states that a location argument (lat/lon or place) is required in practice, nor what happens if none is supplied, which is an important gap for a zero-required-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema itself documents all seven parameters. The description implies proximity ('near a spot'), distance sorting, and the meaning of depth/relief, but adds little parameter-specific syntax or constraint detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (Florida's public artificial reefs) and scope (near a spot, FWC's 4,519 statewide deployments), plus exactly what is returned: name, position, depth/relief, sunk material, year, distance, sorted closest first. No sibling tool covers artificial reefs, so the purpose is immediately distinguishable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names intended use cases (fishing, diving, spearfishing) and one exclusion ('Not for navigation'). It does not name alternative sibling tools for those other activities, but the context is clear enough to route the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond readOnly/idempotent annotations, it discloses the upstream system (Mote Marine), update cadence (~twice a day), the ~131-beach coverage footprint, and a crucial safety caveat that it 'never says the water is safe.' It does not say what happens for a location outside coverage, which would complete the picture.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the flag meaning, but it is one dense run-on paragraph that packs parenthetical flag definitions, a beach list, water-quality notes, and a volunteer-recruitment line together. The Ambassador volunteering sentence is useful for output framing but competes for attention with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return shape and does so (flag meaning, speakable sentence, volunteer info, safety disclaimer). Coverage and freshness are covered; only out-of-coverage/empty-result behavior is unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real semantics by framing lat/lon and place as alternative input modes ('Give a position or a beach/town name'), which the flat schema does not express. It also implies the latitude/longitude pair is a location anchor rather than an independent filter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (the daily lifeguard-reported warning flag at nearby beaches) and its source, cadence and geography. An agent can immediately tell this apart from siblings like beach_water, red_tide or live_conditions because the description enumerates the flag vocabulary and the report contents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied only: 'Give a position or a beach/town name' tells the agent how to invoke but not when to prefer this over beach_water or red_tide, which are adjacent safety/water tools. No exclusions or alternatives are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnly/idempotent annotations by disclosing data provenance, the meaning of an empty result ('no advisory is not the same as a clean test'), and an explicit safety constraint that it never calls water clean or safe. It also previews the response shape (one sentence to say aloud plus the health department link).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core criterion and output are front-loaded in the first sentence, and every sentence carries operational or safety information. The parenthetical county roll-call ('Miami-Dade, Broward, Palm Beach, Tampa Bay, Naples, the Panhandle...') is illustrative padding that could be trimmed without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, five all-optional params, and open-world retrieval, the description covers what is returned (spoken sentence plus official link), the filter modes, and the important negative-result interpretation. Nothing an agent needs to call it correctly or present results safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds real semantic value by explaining how lat/lon plus miles produce a distance-sorted result versus how place triggers name matching, and what happens when both are omitted — behavior the per-parameter descriptions do not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (Florida beach water health advisories), the exact criterion (enterococcus over the state limit with no lift posted), and the data source (the 32 coastal counties' own posts). An agent can tell this apart from beach_flags or live_conditions without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Enumerates the three invocation modes precisely: position + radius for closest-first, place for beach/county matching, and neither for all open advisories in the state. It does not explicitly name a sibling (e.g. beach_flags) as the alternative for general flag status, so routing between siblings is left partly to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false) and open-world scope, so the bar is lower. The description adds genuinely useful behavioral context beyond them: it discloses the scoring inputs (solunar moon, NOAA tide swing, wind/pressure only for the first week) and a reliability caveat — 'Anglers' rules of thumb, never a promise' — which tells the agent how much to trust the output. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in the opening clause, which is good. But the rest is a single sprawling run-on sentence that crams in a full output inventory; the enumerated deliverables could be split or trimmed so each clause earns its place. Density without structure makes it harder to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must explain what comes back, and it does so thoroughly — scores, best-bite hours, top 2 days with tide times, tide-direction-to-habitat mapping, and a spoken one-liner. For a zero-required-parameter, read-only forecast tool this is nearly complete; only input format details are thin.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so lat, lon, and place are already documented, establishing the baseline of 3. The description's 'Give a position or a boat ramp name' confirms the either/or input pattern but adds no syntax, format, or default details beyond the schema. It neither compensates for nor erodes the schema's coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete resource and action: a 1-10 Bite Score for today plus 14 days, best hours, best days, and a current Tide Read. That is far more specific than the title alone. It does not explicitly name a contrasting sibling (e.g., marine_forecast or live_conditions), so an agent must infer the boundary, which keeps it just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by 'When to go fishing in Florida waters' and the input instruction 'Give a position or a boat ramp name.' However, there is no explicit when-to-use-versus-alternatives guidance — nothing tells the agent to prefer marine_forecast for raw weather or live_conditions for current observations. Guidance is present but left largely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only, open-world, idempotent, non-destructive profile. The description adds valuable context beyond that: the FWC inventory source, approximate result count, included county field, closest-first ordering, and the important caveat that live wait data is only available where boaters have reported it and so far only in Tampa Bay.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence with no wasted words, and the key scoping details are front-loaded: resource, geography, source, ordering, and data-quality caveat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only lookup tool with a fully described input schema, annotations covering safety behavior, and no output schema, the description is complete enough: it covers scope, source, ordering, returned fields, and the limitation on live wait coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the lat, lon, and limit parameters are already documented in the schema. The description adds indirect meaning by saying results are 'closest first,' which ties lat/lon to proximity sorting, but it does not clarify the limit parameter or requiredness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (public boat ramps), a precise geographic scope (anywhere in Florida), a source and size (FWC inventory, about 1,600), and the ordering (closest first). This clearly distinguishes it from siblings like fuel_docks, sandbars, and find_places.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'closest first' implies the tool is used for proximity-based lookup near a location, but there is no explicit when-to-use guidance, no exclusions, and no named alternatives. Usage is inferable but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, open-world, non-destructive, so the description only needs to add operational context — and it does: default 8 AM off-ship, up to 3 picks, the trimming rule that guarantees arrival 2h (3h international) before the flight, airport defaults per port, and the caveat that drive times are estimates. It does not discuss result ordering beyond 'in order' or what happens if fewer than 3 places fit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The scenario is front-loaded, which is good, but the single sentence sprawls through stacked parentheticals and re-states defaults (8 AM, 2 vs 3 hours) that also appear in the schema. It is informative rather than padded, but it could be restructured into short scannable clauses without losing content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 parameters, no output schema, and read-only annotations, the description covers the essentials: scenario, defaults, the planning constraint, and roughly what is returned. The missing piece is the mood dimension, an unusual enum whose six values ('old', 'weird', 'road') are not interpretable from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 88%, so baseline is 3, but the description adds genuinely new information: the port→default-airport mapping (MIA, FLL, MCO, TPA, JAX, EYW) and the explicit bags→2-stop consequence. The mood parameter, with six non-obvious values, gets no explanation anywhere beyond one-word schema hints, which is the main gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

It concretely describes the output: up to 3 stops near the port in order, with drive times and a leave-for-the-airport time, for the specific 'off the ship, not yet flying' scenario. That is far more specific than a restated title, and the debark-day framing implicitly separates it from shore_day and draft_float_plan. It lacks an explicit verb up front ('Plan...'), so the purpose has to be inferred from the narrative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Off the ship, not on the plane yet' states the triggering situation clearly, and 'the person decides' sets the advisory (non-booking) posture. The 2h/3h pre-flight constraint and bags=true→2-stops rule further scope correct use. It never names a sibling tool as an alternative or exclusion, so routing vs shore_day or find_places is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior. The description adds important context beyond them: the output is a link with pre-filled fields, and the boater must review and start the trip themselves, meaning the tool does not initiate the trip.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both front-loaded and purposeful. The first explains what is produced, and the second clarifies the user's required follow-up action with no wasted wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With annotations covering safety and idempotency, and the schema covering parameter semantics, the description supplies the missing output behavior (a link) and user flow. It does not cover link expiration or app requirements, but it is otherwise complete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 83%, so the schema already documents nearly all parameters. The description enumerates route, crew, hours, leave time, safety gear, and note as pre-filled fields, which reinforces their role but does not add format or constraint details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool produces a link that opens a pre-filled float plan with specific fields. It distinguishes the action from actually starting the trip by noting the boater checks it and starts in the app themselves, though it does not name a sibling alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'For a boat trip' gives context, and the note that the boater completes the process in the app implies this is a preparation step. However, it does not explicitly state when to use this versus alternatives like open_plan_in_app or what prerequisites exist.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a read-only, idempotent, open-world, non-destructive query. The description adds useful behavioral detail beyond that: it discloses the exact outputs (signal openings, scheduled openings, closures, clearance rules), which helps an agent know what to expect without an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and return details are front-loaded. The long parenthetical list of regions is dense but informative for coverage expectations. Most sentences earn their place, though the regional list could be trimmed without losing much.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six optional parameters, no required parameters, and no output schema, the description does the necessary work: it explains invocation modes and enumerates the return information an agent needs. Nothing critical is missing for correct use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining the two primary query modes—give a position for the closest bridges or give a bridge name—which clarifies how lat/lon/name are meant to be used together. It also mentions 'closed clearance,' loosely connecting to the boat_height_ft parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (Florida drawbridge openings) and exactly what information is returned: signal openings, next scheduled opening, rush-hour closures, call-ahead hours, closed clearance, and the rule. It is clearly distinct from every sibling tool, none of which cover drawbridges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context: supply a position to find the closest bridges or a bridge name to look one up. It does not name an alternative tool or explicitly state when not to use it, but the intended invocation patterns are unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, open-world, non-destructive behavior. The description adds that results are distance-sorted when lat/lon are supplied and that community thumbs and live reports are included only when available, which is useful context beyond the annotations; it does not address pagination/rate limits, but those are less critical here.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description front-loads the purpose but is one long sentence with nested parentheticals listing regions and categories. The content is largely relevant, yet the structure is dense and harder to scan than a short purpose statement followed by scope/category details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-output-schema discovery tool with five optional parameters, the description covers what kinds of places are returned and that live reports may accompany them. It still leaves open default behavior when lat/lon is omitted, what limit defaults to, and what a result object minimally contains, so it is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all five parameters. The description reinforces the category vocabulary (food/beaches/outdoors/oddities/worth-the-drive) and the role of lat/lon in distance sorting, but it adds little for lang or limit and does not explain defaults, so baseline 3 fits.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource — Florida places/things to do — and enumerates the content categories, so the agent knows this is a discovery tool rather than a conditions feed. It does not explicitly name sibling tools or draw a boundary against red_tide/beach_water/live_conditions, which keeps it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage is clear: use it to find things to do and provide lat/lon for closest-first ordering. But there is no explicit when-to-use/when-not guidance and no routing away from sibling tools that cover red tide, water, or live conditions, so an agent could be unsure which tool to call for overlapping data.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, and open-world behavior. The description adds meaningful context beyond that: stamps are earned only by physically standing at the location with the free Headed Back app, which is important behavioral context for an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is reasonably sized and most sentences earn their place by conveying scope, mechanics, and usage. The long parenthetical stamp examples are somewhat decorative but still help convey the tool's domain and are front-loaded enough to orient the reader.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the annotations and the fully described parameter schema, the description gives an agent enough to call the tool correctly. It does not explain the return shape, but with no output schema and a simple retrieval purpose, that omission is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds value by explaining the alternative query modes and listing all 11 region page IDs, which the schema does not fully enumerate. It also clarifies that position input is for finding the closest stamps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a specific resource: the Florida Passport stamp book with 55 stamps across 11 region pages. It implies retrieval by position, page, or name, which is understandable, though it never explicitly states 'returns stamps' and does not directly distinguish itself from broader siblings like find_places.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage contexts such as Florida bucket lists, road-trip stops, and 'what should we not miss,' and explains the three query modes. It does not name alternatives or say when not to use this tool, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description earns credit for what it adds: proximity-based ordering, the per-item payload (teaser, spot, map link), and the fact that the full story opens in the Headed Back app at that place — a real deep-link behavior an agent would otherwise not know.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The front-loaded first clause states the resource and sort order immediately; the example enumerations are colorful but do real work by defining the two content kinds. It is slightly parenthetical-heavy but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully describes the returned item shape (teaser, spot, map link) and the app hand-off. The remaining gap is behavior when lat/lon are absent, since zero parameters are required, which leaves the default result set ambiguous.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% including the enum values, so the schema carries the parameter burden and the baseline is 3. The description adds only implicit semantics — 'closest first' hints that lat/lon drive ordering — but never says what happens if they are omitted, despite no parameters being required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (short true stories about Florida town names and weird spots) and a scope ('pinned all over Florida, closest first'), plus two named content categories. It stops short of differentiating itself from the plausible sibling story_trails, so the agent still has to guess when the two overlap.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'closest first' and 'Great as road-trip stops' suggest a location-driven browse use case, but there is no explicit when-to-use or when-not-to-use statement and no mention of the story_trails sibling as an alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, open-world and idempotent semantics, and the description adds genuinely new traits: result freshness is limited to recently confirmed docks, distances are straight-line rather than navigable water distance, and hours/prices are absent. The phone number is surfaced as an expected return value, though the rest of the return shape is unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single densely packed sentence plus a short caveat sentence; scope, filtering, ordering and limitations are all front-loaded with no filler clauses.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing results, and it does name the phone number, ordering, and the notable missing fields (hours, prices). It stops short of describing the other returned fields (dock name, location/address, fuel types), which slightly limits completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters (lat, lon, limit, diesel) are already documented. The description only indirectly alludes to them via "closest first" and the diesel/gas mention, adding no format or constraint detail beyond the schema; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (public marina fuel docks in Florida) with a clear qualifier (only recently confirmed ones offering gas, diesel or pump-out) and an ordering rule. It is unambiguous against siblings like boat_ramps or inlet_watch, which cover different facilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Closest first" plus the fuel-type qualifier implies the refueling-planning use case clearly, and "call ahead" tells the agent not to treat hours/prices as answers. It doesn't explicitly name an alternative tool or a when-not-to-use condition, keeping it just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, open-world and non-destructive, so the safety bar is already met. The description adds real behavioral detail beyond them: local-time horizon of today and tomorrow, countdown to the next event, sunset bearing, and a four-level sunset rating derived from cloud layers here and 25 miles toward the sun. It stops short of clarifying the case where neither lat/lon nor place resolves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The main clause is front-loaded and dense with useful detail in one sentence. The audience list and the closing 'one sentence to say out loud' are marketing-flavored padding, and the forecast clause makes the sentence long, but almost every element carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing returns, and it does: timing, direction, next event with countdown, verdict levels, and a spoken summary line. Missing is any statement of what happens if location input is ambiguous or incomplete, which matters given all parameters are optional.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so each parameter is already documented, which sets the baseline at 3. The description says 'for any spot', which does not explain the lat/lon vs. place choice and is arguably looser than the schema's Florida-specific 'place' wording, so it adds no meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource and scope: golden hour, blue hour, sunrise and sunset for any spot, today and tomorrow in local time, plus sunset direction and a cloud-layer-based sunset guess. No sibling tool in the list covers solar light timing, so the purpose is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Audience framing ('for photographers, creators, sunset cruises and beach plans') implies usage contexts, but it never says when to pick this over alternatives, nor does it name any sibling. The correct call is inferable but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/openWorld, and the description adds real context beyond them: a 12-hour hourly horizon, the physical rule of thumb being modeled, coverage of 35 inlets, and what the answer says (rough now, easing, or turning rough). It stops short of noting data freshness or update cadence.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core question and 12-hour horizon are front-loaded, and the final sentence usefully summarizes inputs. The enumerated list of inlets is somewhat decorative but does evidence coverage, so it earns partial keep.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining returns and does so ('rough now, when it eases, when it turns rough later'). Inputs, coverage, and horizon are complete; only details like data source/freshness are absent, which is minor for this read-only forecast.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so lat/lon/name are already documented and the description's 'position... or an inlet name' largely restates them. 'For the nearest ones' adds a small point about proximity-based retrieval, but the schema could have carried that itself; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening question plus 'worked out hour by hour for the next 12 hours' and 'Says if it's rough now, when it eases...' define a specific resource (Florida inlet/pass sea-state forecast) and verb (forecast/advise). It never names a sibling alternative, so it is clear but lacks explicit differentiation from tools like marine_forecast or sandbars.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Give a position for the nearest ones, or an inlet name' implies how to query and the two input modes, and the 'stacking up' framing implies when it is useful. There is no when-not guidance and no reference to competing tools, leaving usage inferred rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, open-world, and non-destructive traits, so the description is free to add what they cannot: the upstream source (NOAA GOES-East), a hard staleness window (last 15 minutes), and a geographic restriction (US only). It does not disclose behavior when no strikes exist or when the point falls outside satellite coverage, which is the remaining behavioral gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with resource, source and time window, then the return contents, then the usage trigger — a sensible information order with no filler sentences. Slightly long and chatty in the quoted example, but every clause carries real information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return-value burden and does so thoroughly, including units, directions and the derived 30-minute clock. The gap is that with zero required parameters it never says what the tool does when called with no location at all, nor how it behaves with no strikes in range.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so lat, lon and place are already documented and the baseline is 3. The description adds nothing about the parameters — notably it does not explain the lat/lon vs. place fallback or what happens when all three optional params are omitted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (nearest lightning strikes) with concrete scope (right now, last 15 minutes, US, NOAA GOES-East) and enumerates what is returned: distance/direction/age, counts within 10 and 30 miles, and the 30-minute rule clock. The only weakness is that it never names the closest sibling, storm_watch, so an agent must infer the real-time-vs-forecast split itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear situational triggers — on the water, at a ballgame, beach, campsite, or when asked about storms/lightning — which is strong positive guidance. It stops short of explicit exclusions (e.g., 'not for multi-day forecasts, use storm_watch') or prerequisites, so the when-not side is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already establish that this is a read-only, open-world, idempotent, non-destructive operation. The description adds meaningful behavior context beyond that: the data comes from anonymous reports, is limited to roughly the last 3 hours, and is currently concentrated in Tampa Bay.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence that immediately states the resource and then lists relevant condition types. It is appropriately compact, though the long list and parenthetical caveat make it slightly dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple one-parameter schema and rich annotations, the description covers the key missing context: source, recency, coverage limits, and the kinds of information returned. It does not describe behavior when no recent reports exist, but it is otherwise complete for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the single place parameter is already documented as a place name or place_id from find_places or boat_ramps. The description reinforces that the place is a pier or boat ramp, but it adds little syntax or selection guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as current conditions at a pier or boat ramp and lists the specific condition types reported. It implies differentiation from forecast or official-data siblings through its emphasis on live anonymous reports from the last 3 hours, but it does not explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context: use for what conditions are like right now, based on reports from the last 3 hours. It also includes a useful coverage caveat that reports are mostly from Tampa Bay so far, though it does not state when not to use it or name sibling alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, open-world, idempotent, non-destructive behavior, so the description only needs to add beyond that -- and it does: the output is verbatim NOAA text with no editorial safety judgment, and coverage is limited to Florida waters. It doesn't address what happens for a point outside those waters, which is the main remaining unknown.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, all load-bearing: scope first, contents second, input options third, caveat last. No restatement of the title, no filler, and the caveat is placed where it will actually be read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does it well -- advisories, forecast periods, nearest tide station -- in a tool that is otherwise simple (3 optional params, no nesting). Only the out-of-coverage/error behavior is unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so per-parameter descriptions are already handled. The description still adds real value the schema cannot: it explains that zero parameters are actually required in practice only because you must supply one of the two input routes (lat/lon pair or place), and that `place` accepts a boat_ramps name or place_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names the specific source (NOAA), the resource (marine forecast and tides), and the exact geographic scope (Florida Gulf, Atlantic, Keys, Biscayne Bay, Lake Okeechobee), plus the concrete payload: advisories, next forecast periods in NOAA's own words, and nearest tide station. An agent can distinguish this from live_conditions, inlet_watch, or beach_flags without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the two input routes -- a position or a ramp name from boat_ramps -- and explicitly rules out a whole class of question ("it does not say whether it's safe to go"), which routes safety judgments elsewhere. It stops short of naming the sibling to use for safety or for near-real-time observations, so it lacks full when-not/alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only, idempotent, non-destructive profile, and the description adds genuinely non-obvious context: the data are real drift bottles simulated on real currents every 3 hours, and privacy is guaranteed (never the note, name, or exact spot). It also flags that a spoken one-sentence summary is included, which shapes how the result should be used.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The domain and key promise are front-loaded, and the enumeration of return fields is dense rather than padded. The opening clause about 'earlier versions of our free apps' is promotional filler that does not help an agent decide or call.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates the returned fields and privacy limits, so the agent knows the result shape. The remaining gap is the all-optional parameter set: nothing says what is returned when called with no arguments, or how place overrides lat/lon.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so lat, lon, limit, miles, and place are all documented in the schema itself. The description adds no parameter-level detail — notably it never explains the place-vs-lat/lon tradeoff that matters when none of the five parameters are required. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource and the concrete question it answers ('any bottles washed up near me?'), then lists exactly what comes back (counts, miles away, longest drift, days at sea). That is enough for an agent to know what it retrieves, though the framing is narrative and it never contrasts itself with any sibling tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied through the quoted user question, which suggests 'call this when someone asks about bottles near a location.' There is no explicit when-not, no statement about what happens with zero parameters, and no routing to an alternative for related beach lookups.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so safety is covered. The description adds that the link targets the free Headed Back app on the person's phone, implying a user-facing handoff, but it omits what happens if the app is not installed and does not clarify the return value (is it a URL string, a platform-specific deep link?).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what the tool produces and followed by the usage cue. The '(Play > Explore)' UI path is mild noise but adds orientation for the destination screen, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-optional-parameter, no-output-schema tool, the description covers purpose, inputs, and timing well. However it does not state defaults for omitted mood/start (required=0) or confirm the concrete return form (a link the agent should hand to the user), leaving an agent to infer the last mile of the interaction.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 50% schema coverage and the mood enum exposed as cryptic codes ('old', 'rain', 'wild', 'weird', 'road'), the description usefully expands each into human meaning (Old Florida, rainy day, wild Florida, weird and cool, road trip). The 'start' parameter is already documented in the schema ('early 8 AM, mid 10 AM, late noon'), so the description need not repeat it. The description meaningfully closes the gap on the undocumented enum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly conveys that this produces a deep link that opens the Headed Back app on the user's phone at the 'Plan a day' (Play > Explore) flow, parameterized by mood and start time. It is a specific resource + action, though the noun-phrase framing ('A link that opens...') leaves it slightly ambiguous whether the tool itself launches the app or returns a shareable link. No explicit sibling differentiation, but the capability is distinct enough from tools like draft_float_plan or shore_day.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear conditional: 'Use it at the end of a Florida day plan,' which tells the agent the moment in a workflow when the handoff is appropriate. It doesn't name alternatives or state when not to use it, keeping it just below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/openWorld, so safety is covered; the description adds real value beyond them by disclosing the 8-day data staleness window, the exact severity vocabulary returned, and the 'never says a beach is safe' liability caveat. It does not mention rate limits or data-refresh timing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the resource and time window, then the input modes, then the output and the caveat - a logical order with no filler. The single long first sentence is dense but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of explaining return shape: nearest sites, FWC's own severity words, sample day, miles away, plus a spoken sentence. Combined with full schema coverage this is enough to call the tool correctly; only data freshness and empty-result behavior are unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: zero-argument behavior returns the statewide picture, and place accepts either FWC sample-site fragments or boat-ramp names. The Greeks-style example already lives in the schema; radius default/max is left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a concrete resource (FWC Karenia brevis water samples), a time window (last 8 days) and what comes back (closest sites, FWC severity wording, sample day, distance). An agent can tell it apart from generic condition tools by the 'FWC's own water samples' framing, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives three concrete invocation modes - a position, an FWC sample site or boat ramp name, or nothing for statewide - which is clear operating context. It stops short of saying when to prefer this over beach_flags or beach_water, so no explicit alternatives are offered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so safety is covered and the description is free to add data-shape context. It does: which fields come back, that weather odds appear only 'when posted', that some statuses may be Go/Hold/Scrubbed, and that it emits a single speakable sentence. Minor gaps remain (whether the list is empty when no launches, how fresh the data is).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Scope and time window are front-loaded, and each clause maps to a returned field rather than padding. The long parenthetical of viewing locations is borderline verbose but is genuine return-value information, so it still earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of describing return values — and it does thoroughly, including status values, conditional fields, and the summary sentence. Combined with annotations covering the safety profile and a fully documented 2-param schema, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the enum for 'when' is already documented, so the schema does the heavy lifting. The description only echoes the two-week default via 'in the next two weeks' and says nothing about 'limit' or how the time window interacts with it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (rocket launches), a precise geographic and temporal scope (Kennedy Space Center / Cape Canaveral, next two weeks), and enumerates the return fields (rocket, mission, pad, day/time, status, weather odds, stream link, viewing spots). An agent can distinguish this from siblings like beach_flags or marine_forecast without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger: 'Use it when someone plans an Orlando or Space Coast trip or asks if there's a launch.' That gives clear positive guidance, but it names no alternatives or exclusions — e.g. it doesn't say to use marine_forecast for sea conditions or window_seat for aviation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds useful context about app behavior (e.g., overdue alerts for Headed In, no check-in for Headed Back), but it does not explain the tool's own invocation behavior or return format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core subject ('Our two free iPhone apps') and then details each app efficiently. While somewhat detailed, every sentence contributes relevant context about the apps and no information is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a zero-parameter, read-only tool with no output schema, the description provides sufficient context about the two apps to understand what content the tool likely surfaces. It could be slightly more explicit about the tool's return or action, but it is largely complete for this complexity level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description provides no parameter information, but none is needed, and the schema description coverage is 100% (trivially, for an empty schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names two apps and explains their features, but does not state a specific verb or what invoking the tool actually does (e.g., returns app info, links, or descriptions). It distinguishes the tools' content from marine siblings, but the tool's own operation remains implied rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus alternatives like draft_float_plan or open_plan_in_app. The description is purely informational about the apps and offers no context, prerequisites, or exclusions for tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is covered. The description adds genuinely useful context beyond them: the data comes from the ports' own published schedules, and posted departure times exist only for Miami and Canaveral — a data-completeness caveat an agent would otherwise miss.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what the tool returns and what it covers, followed by use cases. The first sentence is long and parenthesis-heavy (port-by-port viewing spots), which is dense but each clause carries real information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing returns and does so: which ships leave which port, the posted departure time where available, and when each passes named viewing spots. Combined with the annotation safety profile, an agent has enough to decide and call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, and the description compensates by mapping the natural-language scope onto the enums: it names all four ports that correspond to the `port` enum and enumerates today/tomorrow/this week for `when`. The numeric `days` parameter (1–14) is never mentioned, and the interaction between `days` and `when` is left unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a concrete resource (cruise ship sail-aways) and bounds it tightly to four named Florida ports, three time horizons, and specific viewing spots. The scope is unmistakable, though it never explicitly distinguishes itself from near-neighbors like debark_day or shore_day.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives three concrete use cases in quoted/intent form ('can we watch the cruise ships leave', sail-away parties on land, family waving off), which covers the when-to-use question well. It stops short of stating exclusions or naming an alternative tool for schedule/port questions that fall outside this one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already carry readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-structured context: results are 'worked out for any year' (i.e., the big-day dates are computed, not static) and that each entry includes a map plus a qualitative description. No pagination or rate-limit detail, but little else is missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core resource leads the sentence, which is good, but the long geographic roll-call (Tampa Bay through the Panhandle) and the sandbar-name list duplicate what the name parameter schema already shows. Roughly half the text is tourism-flavored enumeration that doesn't guide invocation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Six optional parameters with full schema coverage and rich annotations, and with no output schema the description usefully tells the agent what comes back (description, map, next big day). An agent could call this correctly from the definition as written; only the interplay between miles/limit and positional vs. name lookup is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains lat, lon, name, limit, miles and big_days. The description only restates the same examples ('Crab Island, Beer Can, Haulover') and the big_days flag; it adds nothing about how lat/lon interact, how limit and miles combine, or default behavior. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific resource ('Florida sandbars and raft-up spots', 44 of them) and states the payload an agent gets back: character description, map, and the next big day there. The scope is unambiguous. It never names a sibling (find_places, artificial_reefs, shore_day) that an agent might otherwise reach for, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Give a position, a sandbar name, or big_days: true' enumerates the three invocation modes clearly, which is real routing guidance. There is no explicit when-not/alternative clause, so the agent still has to infer why it would pick this over find_places or artificial_reefs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world, non-destructive, so the bar is lower, yet the description still adds real context: the pier-by rule (45 minutes before all aboard), the cap of 3 picks, the ordering, and the caveat that drive times are estimates and the ship does not wait. It does not say how picks are chosen or how the 45-minute buffer is derived, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single dense sentence plus a use-case sentence, front-loading the scenario and the deliverable before the caveats. It is slightly overstuffed with clause chains, but nearly every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain returns, and it does: ordered picks, drive times, leave time, pier-by time. Combined with the estimate/no-wait caveats, an agent has enough to call this correctly, though how the pier-by buffer or the 3-pick cap is applied is not spelled out.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high (80%), so the baseline is 3; the description still adds meaning by enumerating the port choices in human-readable form and by attaching the all-aboard parameter to the concrete pier-by computation. docks and the mood/lang enums depend mostly on the schema text, so it is not a full 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (a Florida cruise shore day that ends at the pier) and describes the output shape: up to 3 picks near a chosen port, ordered, with drive times, a leave-the-last-stop time, and a pier-by time. It lists the six supported ports. It does not explicitly separate itself from the nearby sibling debark_day, so it falls just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final sentence gives an explicit trigger: use it when someone asks what to do near a Florida cruise port for a few hours. That is clear positive guidance, but no when-not conditions or named alternatives (e.g. debark_day, draft_float_plan) are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and openWorld, so the safety profile is covered. The description adds real behavioral context beyond that: the lists are conditional on a cone touching Florida, units are mph, the source is NHC, and it explicitly frames itself as informational rather than authoritative ('follow the county's orders'). No coverage of what happens with zero active storms or with no parameters supplied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core resource and source, then builds outward to outputs and the conditional list behavior. It is a single dense sentence chain with no filler, though the length pushes readability and a slight pause or two would help scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With zero required parameters, a fully documented schema, an output-schema-less response, and safety annotations already in place, the description supplies enough to call it correctly and know what comes back. The one real gap is behavior when no qualifying storms exist or when no location input is given at all.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3, but the description adds meaning the schema does not: land=true yields a 7-day stock-up list versus a boat tie-down list, and lat/lon is tied to 'when the center passes closest,' explaining why coordinates matter rather than just restating them. The 'place' parameter's role as an alternative to coordinates is clarified as well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (active Atlantic hurricanes and tropical storms), its authoritative source (NHC), and enumerates the returned fields: wind in mph, category, movement, cone coverage, closest approach, watches/warnings, and the tie-down or stock-up list. This is distinguishable at a glance from siblings like marine_forecast or live_conditions, which cover routine conditions rather than active tropical systems.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear context for when to reach for it: cone coverage for a Florida place, a named place, or the lat/lon spot you supply, and land=true toggles the stock-up list instead of the boat list. No explicit exclusions or named alternatives (e.g., vs. marine_forecast or inlet_watch) are given, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the safety profile is covered. The description adds useful context that trails are real places with puzzles and require the free Headed Back app, but it does not explain filtering behavior, output format, or pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single sentence with no outright filler, but the long parenthetical location list is front-loaded after the resource description rather than after a clear action statement. The structure is informative but not crisp for tool selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With four optional parameters, no output schema, and strong annotations, the description need not carry the full burden. Still, it omits how lat/lon and limit are used to select trails, which is important context for invoking a location-based search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so lat, lon, limit, and water are already fully documented in the input schema. The description only implicitly maps walking/biking/boating to the water flag and adds no syntax, default, or filtering details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as short walking, biking, or boating story trails in Florida and adds concrete locations and the required app. However, it does not state the operation the tool performs, such as finding, listing, or returning trails near a location, so an agent must infer the verb from the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides no guidance on when to use this tool versus alternatives such as florida_stories or find_places. There are no exclusions, prerequisites, or context cues beyond the fact that trails are played in the Headed Back app.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: data provenance (30 cities' and counties' own public calendars), the two-week horizon, the ordering rule, and that each result links to its official page.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the scope, then geography/sources, then ordering. Every clause carries information an agent would otherwise have to guess; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 optional parameters and no output schema, the description covers what the tool returns (events with official links), the geographic and temporal boundary, and ordering. Minor gaps remain: no mention of default limit or result-count behavior, and no hint that coverage depends on which calendars publish.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds value the schema does not: supplying a position switches results to closest-first within a radius, and absent a position they come soonest-first. That explains the interaction of lat/lon/miles in a way the isolated field descriptions cannot.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (local events) with explicit scope: Florida, next two weeks, and concrete event categories (festivals, concerts, farmers markets, boat shows, library/park events). The naming of ~30 city/county source calendars and regions (Tampa Bay, Orlando, both coasts, the Keys, the Panhandle) makes it unmistakable against any sibling marine/weather tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Establishes the usage context clearly (what's on, next two weeks) and describes the two operating modes: radius-sorted when a position is supplied, chronological otherwise. It does not name an alternative tool or an explicit 'don't use this for X', though no sibling plausibly competes for event queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world behavior, so the description needn't repeat safety details. It adds genuine value by describing what comes back (drive time, miles, a line about each) and by noting springs are included alongside beaches. It says nothing about result ordering or fallback when an airport has no nearby beach.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the purpose and return contents, then the when-to-use clause. The long airport code list is bulky but each code prevents a bad call, so it earns its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by naming the returned fields and the unit of ranking (drive time). Combined with the full input schema and annotations, an agent has enough to call this correctly. Missing only edge-case behavior such as unknown airport codes or empty results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description earns an extra point by enumerating the 18 valid Florida airport codes, which is more than the schema's single example ('MCO') and directly supports correct input selection. lang and limit are left entirely to the schema, which is fine given their complete descriptions and enum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: from a named Florida airport list, return the nearest beaches and springs by drive time with miles and a short blurb. The scope (airport-to-water drive times) is distinct from every sibling tool, which cover conditions, tides, and planning rather than airport proximity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit triggering scenario: 'when a visitor asks how fast they can be in the water after landing, or which beach is closest to an airport.' It doesn't name a sibling alternative or an exclusion case, but with such disparate siblings that omission costs little.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds real value beyond them: it enumerates the response contents (sights in flight order, left/right side, rough timing, states crossed, GPS tips) and warns about the airplane-mode GPS caveat, which is a behavioral quirk an agent would otherwise not know.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and triggers are front-loaded, but the middle is a long comma-spliced sentence, and the sight list (Lake Okeechobee, Sunshine Skyway, Vehicle Assembly Building, Seven Mile Bridge, Outer Banks, Manhattan, Grand Canyon) is illustrative padding that a two-item sample would have covered. It is informative but not tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry the return shape, and it does — sights, side, timing, states, GPS tips. For a two-parameter read-only lookup that is essentially complete; only the response granularity (how many sights, whether timing is clock or elapsed) is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both airport-code parameters are documented with examples, so the baseline is 3. The description adds meaning beyond the schema by constraining valid values to US airports — Florida's plus large airports with Florida nonstops — which tells the agent which codes will actually resolve rather than leaving it to guess.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete job — recommending which side of the plane to sit on for a US flight and returning sights, side, timing, states, and GPS tips. It is unambiguous and distinct from every sibling (weather, tides, launches, stories), though no sibling is explicitly named as a contrast, which keeps it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names three concrete trigger situations: picking a seat, asking what will be visible from the plane, and asking why a GPS dot disappears in flight. It also bounds the applicable routes (US airports, Florida's plus major nonstop origins). No explicit exclusions, but the positive triggers are clear enough that an agent can route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds no behavioral context of its own — no search radius, no default for limit, no sorting or distance behavior — leaving the geo-lookup semantics undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no bloat, but roughly half its content is origin lore (Ōtsuchi, Japan) rather than operational information. It is succinct without being informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Parameter count is tiny (3, none required) with full schema coverage, annotations cover the safety profile, and there is no output schema to explain. The remaining gaps are the search radius and default limit, which matter but are minor given how simple the tool is.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema documents lat, lon, and limit adequately, establishing the baseline of 3. The description contributes nothing beyond that — it never connects the coordinates to a proximity search or explains what limit counts.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a resource (Wind Phone booths around Tampa Bay) and explains what they are, but never states the operation — presumably a proximity lookup — or what comes back. An agent knows the subject matter but not the action, which is the minimum viable level.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to call this versus siblings like find_places or story_trails, and no note on prerequisites such as supplying coordinates. The only context is thematic ('call someone you lost'), which is not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.