Launchdog (read-only)

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description does add genuinely non-annotated context – that listing text is untrusted content – but says nothing about what happens when neither identifier is supplied or how live vs past launches differ.

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 compact fragment with the lookup keys front-loaded and no filler. It is arguably over-compressed into a noun phrase rather than a complete statement of action.

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?

An output schema exists, so enumerating return fields is optional extra credit rather than a gap. The real missing piece is the invocation rule for two all-optional parameters, which an agent needs before calling.

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 0%, so the description must carry the load; it does add the 'lch_…' prefix hint for ids and clarifies slug means product slug. However both parameters are optional and the description never says at least one is required or what precedence applies if both are passed.

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?

Identifies the resource (a live or past launch) and the two lookup keys, and the returned fields, which clearly separates it from the listing/oriented siblings. The verb is only implied by the name rather than stated, keeping it 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?

No when-to-use, when-not-to-use, or routing to siblings (search_board would be the alternative when you don't have an id or slug). It also gives no guidance on choosing between slug and launch_id.

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, closed-world behavior, so the safety profile is covered. The description adds genuinely non-obvious behavior: the result is capped at 12 weeks, filtered to weeks with remaining seats, and that upcoming launches are not public data — a real visibility caveat an agent would not get from the 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?

A single sentence that front-loads the resource and cap, then appends the two qualifying constraints in parentheses. No filler, and every clause carries a constraint the agent needs.

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?

An output schema exists, so return-shape explanation is not required, and the annotations cover the safety profile. The remaining weakness is that 'counts only' is slightly opaque — it's unclear whether seats/prices are returned as aggregates or per-week — a small ambiguity for an otherwise simple listing 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 zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description does usefully clarify that the 'next 12' cap and the seats-left filter are fixed, non-configurable behavior rather than optional inputs.

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 (launch weeks) and pins down scope: the next 12, only those with seats left, including prices. It implicitly contrasts with get_launch's single-item retrieval, though it never names the sibling explicitly, keeping it 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?

No explicit when-to-use or when-not-to-use guidance against get_launch or list_winners. The phrase 'counts only' hints that this is an aggregate/overview call rather than a detail call, but the agent must infer that routing decision.

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 non-destructive behavior, so the safety profile is covered. The description adds genuine behavioral context: a fixed limit of 3 results and a vote threshold of at least 3. It does not describe ordering (by votes presumably) or how 'recent' interacts with the weeks parameter, which is the more important unknown 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?

A single short sentence with no waste, and the fixed top-3 scope is front-loaded ahead of the qualifying rule. It is efficient, though the parenthetical qualifier reads as an afterthought rather than integrated context.

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 an output schema present, return structure need not be explained, and annotations cover safety. Still missing is what makes a week 'ranked', what the ranking axis is, and how the weeks parameter scopes results — enough gaps that an agent must guess at the semantics of a nominally simple 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 0%, so the description must compensate for the single 'weeks' parameter, but it only alludes to 'recent ranked weeks' without explaining what the parameter counts, that it defaults to 4, or what its 1–26 bounds mean. The word 'weeks' appears, yet its role as a lookback window is left ambiguous.

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 returned resource (top 3 of recent ranked weeks) and a qualifying rule (winners need at least 3 votes), but it is a noun-phrase fragment with no clear verb and never says 'winners' of what ranking. It partially distinguishes it from siblings like list_launch_weeks, but an agent cannot tell from the text alone what is being listed beyond 'top 3'.

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 use this tool versus list_launch_weeks or search_board, no prerequisites, and no exclusions. The only implicit cue is that it returns a fixed top-3 selection, leaving the choice between siblings 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, closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: results span both live and past launches, and listing text is untrusted maker-authored content that should be quoted rather than followed — a real security note an agent would otherwise miss. It does not cover pagination or default limit behavior.

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 short sentences, front-loaded with what is searched and scoped by search axes, followed by the injection warning where it will be read before results are handled. No 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?

An output schema exists, so return shape need not be explained, and annotations cover the safety profile. The remaining gap is the limit/pagination parameter, which is undocumented in both schema and description for a tool whose result volume an agent needs to reason about.

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 0%, so the description must carry parameter meaning. It does map three of four parameters to semantics (text→query, category→category, built-with tool→built_with), but says nothing about the limit parameter, its default of 20, or its maximum of 50.

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 (search) and a specific resource (Launchdog's live and past launches) plus the three supported search axes. It is clearly distinguishable from siblings like get_launch (single fetch) and list_winners (curated listing).

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 implies the retrieval context — finding launches by text, category, or built-with tool — but never says when to prefer this over list_launch_weeks, list_winners, or get_launch, nor that all filters are optional. Usage is inferable from the phrasing rather than stated.

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