Unstocked

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description adds real value beyond them by describing what comes back: parts with typical prices, fitment notes, unlisted items, and a shareable link. It omits failure behavior (e.g., bike or style not matching) and whether results are cached or freshly generated.

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 resource definition, then return contents, then the action to take. The style enumeration duplicates the schema slightly but stays short and readable.

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 so adequately: parts, prices, fitment notes, omissions, and a link. Defaults and accepted inputs are covered by a fully described schema, so nothing essential is missing 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 100%, with bike examples, year fallback behavior, and accepted style values all documented in the schema. The description repeats the style list and mentions model year but adds no new semantics, so 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 states a concrete verb+resource ('A ready-made build for one bike, model year and style') and enumerates the style options, so the agent knows exactly what it fetches. It stops short of differentiating from the sibling make_build_link, which also concerns links, leaving a small ambiguity.

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 a clear output-side instruction ('Give the rider that link'), but no explicit when-to-use versus get_parts or make_build_link, and no guidance on handling an unknown bike. Usage is implied by the resource 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, closed-world and non-destructive behavior, so the description's job is lighter. It still adds real context: the full shape of a returned part (id, category, brand, tier, price, fitment note, flags) and the filtering rule that a year excludes parts not listed for it, plus that stock equipment is included.

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 tight sentences, scope first and return shape second, with no filler. The closing phrase "things to know before buying" is vague, but overall the wording 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?

With no output schema, describing the returned fields and the inclusion of stock equipment is exactly the missing context an agent needs. A read-only listing tool needs little more, though the resource shape (array vs object) is not stated.

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%, with each parameter documented including examples, so the baseline is 3. The description only restates the year/category optionality and says nothing extra about the query matching semantics beyond what the schema already explains.

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?

"Every part Unstocked lists for a bike" gives a specific verb and resource, and the optional year/category scoping is stated up front. It does not explicitly distinguish itself from get_build or list_bikes, though the parenthetical "id (for make_build_link)" shows awareness of the sibling workflow.

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 rather than stated: an agent can infer it should call this to enumerate parts and pass the returned id to make_build_link. There is no explicit "use this instead of X" guidance or statement of preconditions versus get_build/list_bikes.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds that results are grouped by model-year and that returned slugs are reusable downstream, which is genuine beyond-annotation context, but it says nothing about result count, pagination, or what an empty/failed lookup 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?

At three sentences it is not bloated and the query-filter sentence is well placed, but the leading fragment is garbled and front-loads jargon instead of the tool's action. One rewritten opening sentence would make the whole definition tighter.

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, annotation-rich read tool with no output schema, the description is nearly sufficient: it names the returned grouping and explains the slug's downstream role. The remaining gap is minor — no indication of result size or whether an absent query returns everything.

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 single `query` parameter is already documented as "Make or model." The description's examples ("yamaha", "R7", "ZX-6R") add a little color on accepted casing and model formats but largely restate the schema, 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?

The description conveys the resource (bikes, grouped by model-year) and the filterable fields, but opens with the opaque phrase "Bikes Unstocked covers," which reads like internal jargon rather than a verb+resource statement. An agent can infer this is a listing tool, but only from the name and the sentence fragment, not from a clear stated action.

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 the slug with the other tools" implies a workflow link to get_build/get_parts, and the query filter is described as optional. However, it never states when to call this instead of the siblings, nor what the slug is used for concretely, so the routing 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavior: it validates that each id fits the bike, checks for slot collisions, and reports a total at typical prices. That is meaningful beyond the structured metadata, though it does not say whether a failed validation throws an error or returns a diagnostic.

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 tight sentences: purpose first, then input provenance, then validation and return behavior. Nothing is repeated from the schema and no sentence 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?

For a three-parameter, non-mutating link builder with no output schema, the description covers what it produces (a link), what it returns alongside (a price total), and what it validates. An agent could invoke it correctly from this text 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 description coverage is 100%, so the baseline is 3, but the description adds a genuine cross-parameter constraint not in the schema: the part ids must come from the same bike as the 'bike' argument. It also frames part_ids as ordered for display, which reinforces the schema wording.

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 transformation: 'Turn a list of part ids into a link that opens the build on unstocked.bike.' That is a concrete verb plus resource, clearly distinct from the read-only siblings get_build and get_parts, which it explicitly positions as id sources. It stops short of an explicit 'use this instead of X' contrast, so it is not quite 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?

'Use part ids from get_parts or get_build for the same bike' gives a clear prerequisite and names the two tools that produce valid inputs, which is strong when-to-use guidance. There are no explicit when-not-to-use conditions or failure-path guidance (e.g., what to do if an id belongs to a different bike).

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