SkillsPicker

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so 'Read-only' is pure repetition of structured data. The one piece of added value is that the response reports the size of the skill index, which is useful since no output schema exists.

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 a single sentence with useful parenthetical examples. The trailing 'No input needed. Read-only.' fragments are redundant against the schema and annotations but cost little.

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 zero-parameter enumeration tool with no output schema, the description does say what comes back (two tag families plus index size). Minor gap: 'and more' leaves the task-tag taxonomy open-ended, and nothing indicates whether the returned list is exhaustive.

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?

Zero parameters, so the schema carries no semantics to miss; the description correctly confirms no input is required. Baseline 4 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 (List) and two concretely-scoped resources (stack tags: frameworks/languages/services; task tags: testing/code-review/security), plus the consumer (recommend_skills). That framing alone distinguishes it from search_skills, which queries skills rather than tag vocabulary.

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?

'that recommend_skills accepts' implies the intended workflow (discover valid tag values before recommending), but the description never says to call this first or when to skip it. 'No input needed' addresses invocation mechanics rather than when-to-use, and no sibling alternative is 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?

Annotations already declare readOnlyHint/idempotent/openWorld/no-destructive, and the description usefully adds 'Read-only, no account' plus what it does with a repo ('read the file list and manifest files, nothing else'). It also discloses a monetization boundary (2 free picks, $9 for the full list), which is a behavioral trait annotations cannot express.

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, front-loaded with what it returns and how to call it, with the pricing disclosure placed where it belongs. No filler, though it is dense enough that the return-shape and pricing clauses compete for attention.

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 and does it well by describing the result (match count, 2 free picks with license and install command, link to ranked list). Minor gaps remain around failure behavior for invalid repo URLs, but the agent has enough to call it 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 100%, so baseline is 3; the description adds real value by ranking the input options ('tags (best)', one-line description, or repo URL) and by clarifying the no-input fallback, which the schema cannot convey. It does not add tag vocabulary beyond pointing at list_skill_tags.

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 uses a specific verb+resource ('Recommend agent skills') and scopes it to coding projects, naming supported CLIs. It does not explicitly distinguish itself from sibling search_skills, so an agent must infer that this is project-aware recommendation rather than keyword 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?

It clearly states the three input modes and even marks the preferred one ('tags (best)'), plus the no-input default (Next.js sample). It stops short of naming search_skills as the alternative when the caller just wants to browse by keyword.

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?

Discloses traits beyond the annotations: result shape (match count, top 2 skills with license and install command), the existence of a gated full ranked list at $9, and "read-only, no account." The paid upsell-and-truncation behavior is important context an agent cannot get from the schema or annotations. Minor gap: doesn't say how to interpret low/zero match counts or whether the top-2 results are guaranteed.

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 scope and corpus size, then query examples, then return shape, then safety note — a logical progression with no filler. The pricing parenthetical is slightly salesy but is genuinely relevant to result truncation, so it 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?

For a single-parameter, no-output-schema tool, the definition covers scope, query style, return shape, truncation/upsell, and safety. The main missing piece is routing guidance relative to the two sibling tools, which leaves a real decision to inference.

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 documented in-schema with the same example phrasing, so the description is largely redundant here. The example list ("stripe webhooks", "playwright tests", "django admin", "terraform aws") reinforces that the query is free-text task/tool phrasing, which adds slight value. 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?

States a specific verb (search), the resource (90,454 open-license agent skills / SKILL.md), and the axis of search (task, tool, framework) with concrete query examples. This clearly distinguishes it from list_skill_tags (browsing taxonomy) and recommend_skills (suggestion rather than query-driven lookup).

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 the examples ("stripe webhooks", "playwright tests"), so an agent can infer this is keyword-style lookup. However, no explicit when-to-use vs. when-not guidance and no mention of the siblings list_skill_tags or recommend_skills, so the agent must infer which of the three to call.

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