whichlib

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

Annotations only declare readOnlyHint/openWorldHint; the description adds substantial behavioral context beyond them: one GitHub call per repo plus registry lookups, partial-failure semantics (bad repos land in notFound, others still compared), failure only when all fail or rate limit/token rejection occurs, and the hosted quota with the X-GitHub-Token escape hatch. This is a mutation-free read tool whose cost and failure profile are fully disclosed.

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 what is compared, then scoring weights, tiers, verdict, usage, then cost/failure/quota. Long but dense with zero filler; slight length cost from packing the full scoring rubric into one paragraph.

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 carries the return-shape burden and does: score, tier thresholds, verdict, breakdown, and the notFound list. Combined with the disclosed rate limits and quota, an agent has everything needed to call and interpret this 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 description coverage is 100%, and the schema already specifies owner/repo format and the 'not URLs or npm/PyPI package names' constraint, so the description adds little param-level meaning. It restates the 2-10 bound and gives example values, which is marginal reinforcement rather than new information — baseline 3.

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+resource (compare 2-10 GitHub repositories side by side) and immediately enumerates the compared dimensions and the returned fields. It explicitly contrasts itself with the sibling recommend_repos, so an agent can route between them without opening a 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 explicit when-to-use ('choose between candidates you already have, for example zod vs valibot' / 'check a dependency the project already uses') and names the alternative for the opposite case ('use recommend_repos to find candidates'). Nothing 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 only cover readOnly and openWorld; the description adds substantial operational context: it makes 3 GitHub searches plus npm/PyPI lookups, is subject to a 50 calls/day hosted limit, accepts an X-GitHub-Token header for unlimited use, and can run locally via npx. These are real behavioral traits beyond structured data.

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 purpose and routing, then the scoring model and operational notes. It is dense and long, but every clause is load-bearing for interpreting results; minor tightening could still help.

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 describe returns, and it does thoroughly: 0-100 score, weighted components, tier thresholds, one-line verdict, and full breakdown. Coupled with rate limits and auth, an agent has everything needed to call and interpret this 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 the baseline is 3, but the description adds meaning beyond the schema by defining the fitness formula (fit = score x relevance to the need) and clarifying that `need` gets reinterpreted through relevance weighting. It reinforces limit usage but adds little on language.

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 the best open-source library for a need) and pins the moment it applies (before adding a dependency). It also names the sibling it is not: compare_repos is for when you already have names, so it is distinguishable without opening any 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?

Explicit when-to-use ('you do not yet have candidates') and the alternative with its own condition ('use compare_repos when you already have names'). This is unambiguous routing between siblings.

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 only cover readOnly/openWorld; the description adds the real operational facts an agent needs: one GitHub search (or a raw.githubusercontent.com download for rising), one npm/PyPI lookup per repo when withDownloads is true, and a 50-calls/day quota with the X-GitHub-Token header or local npx fallback. It also discloses return semantics (0-100 score, weightings, tier thresholds, verdict, breakdown), far beyond what annotations 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?

Purpose and the key exclusion are front-loaded in the first sentences, and every later sentence (call budget, scoring, tiers) carries usable information. It is dense and long, and the full scoring weightings could reasonably live in docs, keeping it short of a 5.

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 fully covers the return shape (score, tier, verdict, breakdown), cost model, auth/quota, and alternative tool choice. An agent has everything needed to call it correctly 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 baseline is 3, but the description adds interpretation the schema lacks: that 'rising' tracks repos of any age via stars gained this week, and that risingRank/starsRank control the returned ordering. It does not restate limit or language beyond the schema's own text.

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 ('the most-starred GitHub repositories created in the last day, week or month') and contrasts with a named sibling ('use recommend_repos for that'). An agent can distinguish it from compare_repos/recommend_repos without opening a 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?

Explicitly says when NOT to use it ('Not the right tool for picking a dependency, since new repositories have little maintenance history') and names the alternative (recommend_repos). It also explains what each period value selects and when withDownloads adds cost.

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