WithBy

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's extra burden is low. It still adds real value by disclosing the account prerequisite ('Needs their WithBy account') and the shape of the result (road-order list with per-story length), which annotations cannot convey.

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 short sentences, front-loaded with the usage trigger before the mechanics and prerequisites. Every sentence carries distinct information: when to call, what is returned, account requirement, scope exclusion.

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 zero parameters, the description adequately covers what the agent needs: the trigger, the account requirement, and the returned content (road order, story length). It is slightly thin on what happens with an empty list or whether the list is per-user or shared, but nothing critical is missing for a simple read 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?

The tool takes no parameters, so the baseline is 4 and there is no schema semantics the description needs to compensate for. The description correctly implies no filtering arguments are 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?

States a specific verb and resource ('Lists their WithBy next-drive list') and adds the ordering and payload ('road order with each story's length'), so the agent knows exactly what comes back. It does not distinguish itself from actual siblings such as save_for_drive or story, instead excluding unrelated domains (navigation, bookings), which limits sibling differentiation.

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?

'Use this when someone asks which stories they saved for their next drive, or which one comes first' gives a clear, concrete trigger tied to user phrasing. It also states a negative boundary ('Not for navigation or bookings'), though it never names the sibling tool an agent should call instead for saving or fetching a single story.

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, non-destructive and open-world, so safety is covered. The description adds real value beyond that by describing the response shape: one-line verdicts for Snoqualmie, Stevens, White and Blewett, then 12 other passes in WSDOT's words with seasonal closures marked, then out-of-area passes, plus a check timestamp. It stops short of detailing freshness guarantees or what happens when an agency feed is unavailable.

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 triggering condition, then the return structure in a single ordered sentence that mirrors the response layout. It is dense but every clause carries information; the phrase "Gives WithBy's verdict" is slightly clunky but not padding.

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 present, the description must carry the return-value burden and does so in detail: section order, sourcing attribution, closure marking, and timestamping. Combined with annotations covering the safety profile and a zero-parameter schema, 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?

The tool takes no parameters at all, so per the baseline this sits at 4. The description correctly spends no words on inputs and instead invests in output content, which is the right allocation for a zero-argument tool.

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 with scope: "Washington's mountain passes in depth, and the passes on the roads out of it," and explicitly frames the tool as the general/whole-list answer. The contrast with a single-pass status check is implied by "in general" and "the whole list," enough for an agent to pick between this and pass_status.

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 opening sentence gives concrete triggering conditions (general mountain-pass questions, which passes are open, wanting the full list) and the closing sentence excludes navigation and bookings. Strong, though it never names the sibling pass_status as the alternative for a single-pass lookup, so the routing 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?

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds real substance beyond that by disclosing data provenance (WithBy verdicts vs WSDOT's own words), differing depth per pass, and that every answer carries both the check time and the agency report time. It stops short of covering edge behavior, e.g. what happens for an unrecognized or misspelled pass name.

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 usage trigger, then coverage, then output guarantees, then exclusions — a sensible order with no filler sentences. The sentence 'Covers Washington's mountain passes in depth, and the passes on the roads out of it, in their agency's words' restates coverage already given in the prior sentence and could be cut.

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 a single fully documented parameter, no output schema, and annotations covering safety/idempotency, the description supplies everything the agent needs: what is covered, which sources back which passes, and what each answer contains. Ambiguity handling for unknown pass names is the only remaining gap and is minor at this complexity.

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 gives name examples, so the baseline is 3. The description earns a bump by enumerating the queryable set (Snoqualmie, Stevens, White, Blewett, the two bridges, plus 12 other passes), which helps the agent construct a valid 'pass' value; it does not explain matching behavior for ambiguous input.

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 concrete set of questions the tool answers (is the pass or I-90/SR 520 floating bridge open, what are the restrictions/chain rules, how long the crossing takes) and names the exact passes and bridges covered, so the resource and scope are unambiguous. It does not differentiate itself from the sibling 'passes_now', which by name sounds like an overlapping status tool, so the sibling distinction is left to inference.

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?

Trigger conditions are explicit ('Use this when someone asks whether...'), and there is a clear exclusion ('Not for navigation or bookings'). What is missing is the positive alternative: it never says when to prefer 'passes_now' or 'my_next_drive' instead, which matters given the near-duplicate sibling name.

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=false, destructive=false, idempotent=true and openWorld=false, so the description only has to add context beyond that. It does: an account requirement ('Needs their WithBy account'), the append-to-existing-list nature of the write, the capacity bound, and the fact that this mutates the same list as the website action. It does not say what happens to ids already on the list (relevant given idempotentHint=true) or what a successful call returns.

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 front-loaded sentence: trigger first, mechanism second, boundary last, with no filler. It is dense to the point of being a long run-on colon construction, and the 'same list as Save for my drive on withby.ai' clause could be tightened, but nothing 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 one-parameter append tool with full annotation coverage and no output schema, the description supplies the non-obvious pieces an agent needs: authentication requirement, target list identity, and domain scope. The one remaining gap is outcome semantics — duplicate ids and the success response are unspecified, which matters slightly because no output schema exists to fill that in.

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% on the single story_ids parameter, so the schema already explains format, bounds and provenance. The description's restatement of the 1–50 range and the id source duplicates that rather than adding meaning, 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?

States a specific verb and resource: it adds 1 to 50 stories, by id, to the user's WithBy next-drive list, and anchors that list to the visible 'Save for my drive' action on withby.ai. The sentence 'Not for navigation, bookings or places outside Washington' plus the id-provenance clause ('the ids the story, stretch and nearby-stories answers give') distinguishes it from siblings such as my_next_drive, story and stories_near.

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?

Opens with an explicit trigger ('Use this when someone wants particular stories saved for their next drive') and gives clear exclusions (no navigation, no bookings, no places outside Washington). It stops short of naming the sibling tools to redirect to — e.g. my_next_drive for viewing the list, stories_near for discovery — so the alternative routing is left implicit.

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 the safety profile is covered. The description adds genuinely new behavioral facts: results are capped at up to 3, and if nothing matches it falls back to 'nearest covered towns', plus a geographic boundary of Washington — all of which shape how an agent should interpret a thin result set.

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 load-bearing: the trigger and scope come first, then the return behavior and exclusions. No filler, no restatement of the title, and the most decision-relevant constraint (Washington-only) is placed where it will 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?

For a one-parameter read tool with rich annotations, the definition covers trigger, scope, result cap, and fallback behavior, which is most of what an agent needs. There is no output schema, and the description does not indicate the shape of a 'story' record or whether a fallback to nearby towns is distinguishable from an exact match, a minor remaining gap.

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 already documents the accepted town/city/landmark/highway forms with identical examples. The description restates the same meaning rather than adding syntax, disambiguation, or normalization rules 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 verb and resource ('what stories Sal has near a town, city, landmark, or highway') and narrows scope to Washington, with concrete example inputs. It does not name the closer siblings (story, stretch_stories), so an agent must infer the distinction from the 'near a place' framing rather than being routed 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?

Opens with an explicit trigger ('Use this when someone asks...') and closes with clear exclusions ('Not for navigation, bookings, or places outside Washington'). It stops short of naming which sibling tool to use for a single known story vs. a route-based request, leaving that alternative unstated.

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 the safety profile is covered. The description adds genuine value beyond them by enumerating the return payload (Sal's story, place and stretch, length, Wikipedia/source credit) even though no output schema exists, and it stays consistent with openWorldHint by limiting scope to Washington highways. It is silent on what happens when no story matches (empty result vs. error) and on any fuzziness in matching.

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, no filler: the trigger condition comes first, then the return contents, then the exclusions. Every clause carries information an agent needs, and nothing is repeated from the schema or annotations.

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 single-parameter read tool with rich annotations and no output schema, the description is nearly complete: it gives the trigger, the domain limit, and the return fields. The only notable omission is resolution behavior when a query matches nothing or matches multiple places, which would matter for a name-based lookup.

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 parameter already documents that it accepts an id, title, or place name with examples, so the schema does the heavy lifting. The description restates the same three lookup modes without adding syntax, matching behavior, or format constraints, which is the baseline case for full schema 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 verb+resource (retrieve Sal's story for a place/landmark/town along Washington highways, or by id) and lists what comes back (story text, place and stretch, length, source credit). It bounds the domain to Washington, which separates it from generic lookup tools, but it never names the closest siblings (stories_near, stretch_stories), so the boundary there is left to inference.

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 explicit when-to-use guidance ('Use this when someone asks for a story about a place, landmark, or town... or asks what Sal knows about a specific location or story by id') plus explicit when-not guidance ('Not for navigation, bookings, or places outside Washington'). The gap is that the exclusions target unrelated task categories rather than the real alternatives in the sibling set, so an agent comparing this to stories_near or stretch_stories gets no routing advice.

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. The description adds context the annotations cannot: results come back ordered for driving with per-story durations and a total time, and the data set is confined to Washington roads — useful for setting expectations on a tool with no 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?

Three sentences, front-loaded with the usage trigger, followed by concrete examples and then exclusions. No redundant or filler wording; every sentence carries decision-relevant 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?

For a simple read-only lookup with two well-documented parameters and no output schema, the description covers trigger, input forms, exclusions, and return content. Only minor gaps remain, such as whether an empty stretch yields an empty list versus an error, and no explicit sibling routing.

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 including the direction enum. The description still adds value by showing the two accepted input shapes side by side (road+direction like 'I-90 west from Seattle', or a stretch id like 'sr520-03'), which confirms that an id alone is valid without a separate direction.

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?

Description names a specific verb+resource (return Sal's stories along a given highway stretch), states the scope (Washington only), and says what comes back (stories in driving order with durations and total time). The stretch-based framing implicitly separates it from the point-based sibling stories_near and the single-item sibling story.

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 ('when someone asks what stories Sal has along a highway or stretch of road') plus examples and clear exclusions ('not for navigation, bookings, or roads outside Washington'). However, it never names alternatives such as stories_near or story for cases where the user gives a location rather than a stretch, so routing between 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.