Swell Cabin

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

Annotations already cover readOnly/idempotent/non-destructive, so the description's value is in constraints: only readings from the last 3 hours, buoy-implausible readings dropped (leftOut with reason), and the caveat that these are AI readings of a picture, not measurements. It also documents ordering (towns by best spot's score, spots best-first) and the standout-null rule, which are non-obvious behaviors. It falls short of a 5 only because the density makes some of this hard to extract.

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 opening is front-loaded, but the body is a wall of nested parentheticals and semicolon-chained clauses that is far harder to parse than the two-parameter tool warrants. Since there is no output schema, describing return fields is justified, but the same content could be half the length and structured into sentences.

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 only two trivial parameters, the description carries the full burden of explaining return shape (words, surface, shape, crowd, sure, verdict, label, reason, forecast, buoy, score, cams, rank, best, standout, leftOut) and does so comprehensively. An agent can call this correctly and interpret the result without additional context.

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 real semantics: without town the result spans every town with a current reading and towns are ranked by their best spot, and good filters to spots that look good. That is behavior the schema's one-line 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?

The description opens with what the tool returns: AI readings of surf-cam stills, spot by spot, with verdicts, plus a positioned contrast against surf_forecast. However, the actual verb (fetch/read) is buried under a dense enumeration of return fields, so the agent has to parse a long run-on before confirming the tool retrieves cam readings.

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 an explicit trigger phrase ("is it good right now at …") and a fallback ("readings is empty ... use surf_forecast"), plus the meaning of the good filter, and it tells the agent to say standout is unclear when null. It does not distinguish this from the sibling surf_now or surf_cams, which likely could be confused with it.

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 declare a safe, idempotent, closed-world read, so the description need not argue safety. It does add genuine value by disclosing that results are sorted by distance and that the dataset is curated, but it omits what happens with a call containing no filters and how town and lat/lng interact when both are 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?

Two sentences, both dense with information, with the return shape stated first and the two search strategies second. There is no filler, no restatement of the tool name, and nothing that could be cut without losing meaning.

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's field list is helpful, and it covers both spatial entry points. But for a 7-parameter tool with zero required parameters, it leaves the agent guessing what an unfiltered call returns and whether town and lat/lng are mutually exclusive or combined.

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 only 29%, so the description carries real weight, and it does clarify that town is a slug and that radius_km pairs specifically with lat/lng. However, the limit, type, level, and lat/lng parameters get no added meaning, and the implicit beardown of 7 parameters leaves several semantics documented only by their names.

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 pairs a specific verb with a specific resource and enumerates the payload ('exact coordinates, break type, direction and level'), so an agent immediately knows what comes back. It does not distinguish itself from the sibling surf_pools, which is a real ambiguity because 'pool' is also a value of its own type enum.

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 modes — a town slug search versus a lat/lng plus radius_km search — which tells the agent how to drive the tool. It never states when to prefer this tool over surf_pools, surf_cams, or surf_forecast, nor does it set any exclusions, so tool-selection guidance is only implied.

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, so the safety profile is covered. The description goes further by explaining that dataQuality carries a 0–100 trust score with audit warnings and that surfByMonth is a three-year measured statistic (NASA JPL MUR SST), explicitly not a forecast — real interpretive context an agent could otherwise misreport.

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 front-loaded correctly with the resource and its contents, and with no output schema much of the length is earned. But it is delivered as one dense, comma-spliced block with nested parentheticals (facing, tide, tideSources, clips[].url) that is hard to scan and buries the two most actionable instructions near the end.

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 full burden of documenting returns, and it does so thoroughly: field-by-field meaning for dataQuality and surfByMonth, photo licensing, and clip URLs. Minor gaps remain — it does not say what happens for an unknown slug, nor clarify formats for 'season' or 'levels'.

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?

Only one parameter exists and the schema documents it fully at 100% coverage (slug from search_towns, with an example). The description adds nothing about the slug's format or behavior beyond what the schema already states, so the 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?

Opens with a specific verb and resource ('Full profile of one surf town') and enumerates the exact contents: description, season, water temperature, wave types, levels, spots, photos, clips, dataQuality and surfByMonth. That is far more specific than the name alone. It never explicitly contrasts itself with search_towns or town_feed, so the sibling differentiation is only implied by 'one surf town' versus a search.

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?

There is no statement of when to call this instead of search_towns, town_feed or surf_now; the agent must infer that this is the detail lookup after a search. The description does give output-usage guidance ('use surfByMonth for when should I go', 'tell the user when trust is low'), which is useful but is not tool-selection 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 cover the safety profile (readOnly, idempotent, non-destructive, open world), so the description is credited for going beyond them. It discloses data provenance that materially affects trust in results: stays and food/surf businesses are saved merged OSM+Overture collections, while 'spots' is a live OpenStreetMap lookup — a meaningful freshness difference between categories. It also specifies the photo sub-object contract ({url, page, author, license}) and licensing condition, which no annotation conveys.

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 category map is front-loaded, which is good, but it is buried inside nested parentheses ('spots (Surf spots (community mapped))') that are hard to parse. The long parenthetical enumeration of stay types (hotels, resorts, hostels, surf camps, guesthouses...) consumes significant space for marginal selection value. The final sentence about photos is useful and 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, and the description does an unusually good job of describing return payloads: which fields stays carry (website, phone, email, socials, stars, rooms, facilities), and the shape of embedded photos. Combined with the category-to-data-source mapping, an agent knows what it will get back. Minor gaps remain around pagination/limit semantics and the spatial default when radius_km is omitted.

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 only 40%, so the description must compensate. It does useful work by expanding the 'category' enum into readable buckets and describing what data each collection yields (stay fields, photo object shape), but it says nothing about limit behaviour or radius_km even though ordering by distance implies a radius filter. With annotations already declaring readOnly/idempotent/openWorld, the behavioral burden is lighter, hence 3 rather than 4.

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 (places around a surf town) and a specific ordering rule (sorted by distance), then enumerates the five category buckets with their labels. An agent can immediately tell this is a distance-sorted place listing. It stops short of distinguishing itself from the sibling find_surf_spots, whose scope partially overlaps the 'spots' category.

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 category breakdown; there is no explicit statement of when to choose this over find_surf_spots or search_towns, and no exclusion guidance. An agent can infer this is the tool for lodging/food/coffee/surf-business listings near a known town, but the routing decision against siblings 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 a safe read-only, idempotent, closed-world operation, and the description goes well beyond them: it discloses the default ranking basis (popularity.rank 1 = best known, derived from Wikipedia readership, places to stay, surf spots), the alternate ranking when a month is supplied (good + great days over three years at the town's best spot), and that the default excludes towns without curated spots. It also notes null semantics for seaTempC and waveHeightM, which is the kind of caveat an agent needs to interpret results.

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, purpose front-loaded, then a dense but purposeful second sentence covering ranking and return fields. Every clause carries information, though the month-ranking clause is long and could be split for scanability.

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 and no output schema, the description usefully documents the returned fields (best months, water temperature, spot count, page URL, inMonth goodDays/greatDays, seaTempC, waveHeightM). Gaps are minor: it does not describe limit/pagination behavior or the meaning of the level and break_type enum values, which are the least self-explanatory remaining parameters.

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 50%, with level, limit, region and break_type undocumented in the schema, but the description compensates by naming surfer level, wave type and region as filter dimensions. It also adds meaning beyond the schema for month, clarifying that it both filters ('month with good surf') and switches the ranking metric, which the schema text alone does 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 verb and resource ('Find surf towns') and enumerates the filterable dimensions: name/country text, region, month, surfer level, wave type. It reads clearly as a discovery/list tool, but never names a sibling such as find_surf_spots or get_town to draw the boundary 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?

'All filters are optional' implies the no-filter browse case, and the month filter's effect is explained. However, there is no explicit statement of when to reach for this instead of the overlapping siblings (find_surf_spots for spots, get_town for detail, nearby_places for proximity), so the routing 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 readOnlyHint=true and destructiveHint=false, and the description is consistent with that: proposals are approved by the owner and dispatched through Buffer, so the tool itself does not publish. It adds genuinely useful behavior beyond the annotations — per-network formatting, UTC send times, PNG card/story output, fact provenance, the well-known-spot naming constraint, and the no-'today/tomorrow' rule. It does not state volume limits, pagination, or how many posts come back.

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 first sentence runs to several hundred words with deeply nested parentheticals enumerating every post type, which buries the operational facts an agent needs. Later sentences are comparatively readable, but the whole is a wall of text where 'a full inventory of content types' displaces the front-loaded essentials.

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 one optional parameter and no output schema, the description carries the full burden of describing returns, and it does so in detail: networks, timestamps, links, card images, and grounding facts. The enumeration of evergreen and weekly post kinds is more taxonomy than an agent needs to call the tool, but nothing critical to correct invocation 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% and the schema already explains that the town slug is optional and what omitting it does. The description still adds meaning beyond the schema: results are for that town 'now, best first', which conveys ordering and recency semantics the schema does not.

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 clause, 'What Swell Cabin posts on social media, worked out from its own data,' plus the 'With a town' / 'Without a town' split makes clear this returns/generates social post proposals and lists scheduled posts. It is a noun phrase rather than a verb+resource, and the dual identity (proposal generator for one town vs. latest global proposal + scheduled list) is buried mid-sentence rather than stated up front, so the agent must read a long way to confirm the operation.

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 description explicitly distinguishes the two calling modes: pass a town to get that town's ranked posts, omit it to get the latest daily proposal across every town plus what is already scheduled. There is no reference to sibling tools (whats_on, town_feed) and no statement of when not to use it, so it stops short of full 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 goes well beyond them: it discloses that only cams Swell Cabin actually opened and checked are returned (Surfline last), that no search links are included, and what verifiedPlaying, live, pinNote and the embed kinds mean. That is exactly the extra behavioral context the annotations cannot carry.

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 purpose is front-loaded, but the body is one very long run-on sentence dense with nested parentheticals (embed kinds, network names, permission dates) that is hard to scan. The information earns its place, but the structure does not.

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 full burden of explaining return values, and it does: it defines verifiedPlaying, live, embed kinds (youtube/still/player/null), permission, pinNote, networks and search. An agent knows what it will receive and how to interpret it.

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 both parameters are already documented, and the description adds only the framing that `spot` narrows to one of the town's spots. Baseline 3 is appropriate since the schema does the heavy lifting.

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 clause states a specific resource and scope: 'Live surf cams for a town or one of its surf spots,' which tells an agent exactly what comes back. It does not, however, distinguish itself from the sibling cam_now, so the agent must infer the split between the two cam tools.

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 one concrete routing hint — use `networks`/`search` for spots without a saved cam — and notes that only checked cams are listed. It never says when to prefer this over cam_now or surf_now, so the when-to-use guidance is implied rather than explicit.

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 the supplied annotations, the description discloses that results are cached for up to 3 hours, names the underlying wave and wind data sources, explains confidence methodology across three models, and describes nowcast scaling and caveats about trusting water temperature only when the source is satellite or climate. This is substantial behavioral context that annotations alone do not provide.

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 main purpose, but it then becomes an extremely dense, semicolon-heavy block with deeply nested parenthetical detail. Much of the output detail is useful because there is no output schema, but the structure is difficult to parse and would benefit significantly from breaking the material into shorter sections.

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 tool's complexity and the absence of an output schema, the description is remarkably complete: it explains forecast fields, confidence and model comparison, accuracy and buoy correction, offshore satellite checks, now, live observations, and nowcast scaling. An agent has enough context to understand what the tool returns and how to interpret the caveats.

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 schema already defines town as a town slug and spot as an optional spot name from get_town. The description adds little parameter-specific guidance beyond reinforcing that forecasts cover a town and each of its spots, so the high-coverage baseline of 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 description opens with a specific verb and resource: 'Live 7-day surf forecast for a surf town and each of its spots, rated hour by hour.' It clearly distinguishes this forecast tool from current-condition siblings like surf_now and surf_cams by emphasizing the 7-day outlook and per-spot hourly ratings.

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 by 'Live 7-day surf forecast' and the forecast-vs-now distinction is clear in context, but the description never explicitly says when to use this tool versus surf_now, surf_cams, or find_surf_spots. It also does not state that the optional spot should come from get_town, leaving that to the schema.

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 the description adds substantive context beyond them: data is regenerated twice a day, a stale flag means more than 36 hours old, results are ordered best-and-soonest, and day labels are resolved in each town's local time. Those are behavioral traits an agent cannot get from the schema or 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 purpose and the sister-tool pointer are front-loaded, which is good, but the core is one long run-on sentence with nested parentheses listing return fields. It is dense enough that key details (stale threshold, ordering) are easy to skim past.

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 enumerating return content (day, rating, spot, best time, surf description, forecast confidence, local day name, today's rating) and mentions sharing each town's url. The gaps are the undocumented limit and region parameters rather than missing result semantics.

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 only 25%, and the description compensates for two of four parameters: within_days ('from today up to within_days ahead') and min_rating ('at least min_rating'). region and limit are never mentioned, so the agent gets no hint about regional scoping or what limit truncates.

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 ranking rule: towns whose best day within the window meets min_rating, ordered 'best and soonest first', with the fields each result carries. It also explicitly distinguishes itself from surf_forecast (one town's full forecast), so an agent can route without opening either 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?

Gives an explicit trigger phrase ('where is it good right now / this weekend') and names the natural follow-up tool, surf_forecast, for drilling into a single town. That is a when-to-use plus an alternative, not just implied context.

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 closed-world, so the baseline is low-hanging. The description adds real value beyond them: nearest-first ordering with distances in km, the 250 km default / 5000 km max radius, the 'where published' caveat on wave technology, and disclosure that each record carries a last-checked date and its sources. It still doesn't say how large the full result set is or whether output is truncated.

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?

Appropriately front-loaded and free of filler, but the first sentence is a long run-on that packs example pool names and a full field inventory into one breath, which costs scanability. Splitting the field list from the identity sentence would make it easier to parse.

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 and no output schema, the description does the work of describing the return shape (city, country, coordinates, technology, levels, website, notes, last-checked date, sources), which is exactly what's needed. Feedback coverage is slightly incomplete on result-size limits and on what a town-slug search does when nothing is within radius.

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 combination semantics the schema does not state — the four mutually exclusive search modes including 'nothing for all of them' — and confirms nearest-first ordering with km values for town searches. The level filter is only lightly touched ('good for beginners and for training') compared to the explicit enum in 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 (public wave pools/surf lakes) with named real-world examples and enumerates the returned fields, so the agent knows exactly what this returns. It never names a sibling tool to differentiate itself, but the inland/public-pool scope is specific enough to separate it from generic spot or cam tools.

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 invocation contexts (town slug, lat/lng, country code, or no argument for everything) and adds a genuine selection cue: pools are inland, work when the sea is flat, and suit beginners/training. It stops short of explicitly naming alternatives such as find_surf_spots or surf_cams, so the when-not guidance is implied 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?

Beyond the annotations, the description discloses extensive behavior: the quality check and what it drops, ranking of promos and clickbait, YouTube fetch cadence and quota constraints, Instagram reel handling, language filtering, town "all" aggregation, top ranking rules, and exclusion behavior. It does not contradict the readOnlyHint, idempotentHint, openWorldHint, or destructiveHint 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 description is a very long, dense paragraph with nested parentheticals and implementation details such as YouTube quota timing and Instagram Business Discovery. Although it starts with a high-level purpose and labels many fields, its run-on structure makes it difficult to scan and includes more detail than an agent needs for 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?

There is no output schema, so the description must carry the return-shape burden, and it does: it enumerates the feed sections, item fields, quality metadata, language behavior, classics, and town "all" output. For a complex composite feed tool, this is complete enough for an agent to understand what will be returned.

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 high at 80%, so the baseline is 3, but the description adds substantial meaning for town "all," review's dropped items, languages filtering, and exclude. The only notable gap is that the limit parameter is not described in either the schema or the description.

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 the town's Feed and enumerates what it contains: insights, posts, videos, Instagram posts, articles, classics, quality metadata, and the town "all" variant. It does not explicitly differentiate this composite feed from siblings such as social_posts, whats_on, or surf_now, so it falls 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 description explains what the feed contains and how town "all" behaves, but it gives no explicit when-to-use guidance, no when-not-to-use conditions, and no named alternatives among the sibling tools. Usage is only implied by the word "Feed," which is not enough for strong selection 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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description goes beyond that by disclosing the timezone basis for results, the default time window, and the coverage failure mode (covered: false). It also states that every entry carries a source, which is a meaningful trust signal. It stops short of describing result ordering 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?

Three sentences, front-loaded with what the tool returns before the defaults and the coverage caveat. The long parenthetical category list is dense but earns its place by scoping exactly what counts as 'what's on'; nothing 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?

With no output schema, the description carries the burden of explaining returns and does so: a weekly schedule, dated events, a scene summary, a per-entry source, and a coverage flag. Combined with the local-time and default-window notes, an agent has everything needed to call it and interpret the result.

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 both parameters, which sets the baseline at 3. The description adds the important semantic that omitting 'day' yields tonight plus the coming week rather than a single day — a default the schema does not encode — but gives no extra help on the 'town' slug format.

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 concretely — recurring nightly schedules (parties, live music, DJs, comedy, movie nights, games, salsa, markets, culture) plus upcoming dated events in a surf town — so an agent knows exactly what content comes back. It does not explicitly contrast itself with overlapping siblings like town_feed or social_posts, 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 conveys the default window ('tonight and the coming week, in the town's local time') and a real precondition ('some towns aren't covered yet (covered: false)'), which is useful context for deciding whether to call it. However, it never names an alternative tool or says when a different sibling (e.g. town_feed) should be preferred, so usage guidance is implied rather than stated.

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