whichlib

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

Goes far beyond the readOnlyHint/openWorldHint annotations: it discloses the scoring formula and weights, tier thresholds, the one-API-call-per-repo cost, npm/PyPI lookups, partial-failure behavior (notFound vs total failure), rate-limit and token-rejection failure modes, and the 50-call/day hosted quota with the X-GitHub-Token escape hatch. This is unusually rich operational context.

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 core comparison purpose and output, and every clause carries real information (weights, tiers, failure modes, quota). It is a dense single paragraph rather than a tautological one, though the sheer density slightly hurts scannability.

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 still explains return values (score, tier, verdict, breakdown) and the notFound container, and it covers auth, rate limits, and failure conditions. Nothing an agent needs to call this correctly is missing.

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 it already documents owner/repo format and the 2-10 range, so the baseline is 3. The description still adds value by emphasizing 'known' repositories (i.e. ones that must exist and can land in notFound) and repeating the 2-10 bound in context, reinforcing the constraint beyond the raw 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 (compare) and resource (2-10 known GitHub repositories), plus the output shape (score, tier, stars, forks, verdict). It explicitly distinguishes itself from recommend_repos in the same sentence, so an agent can route between the two siblings without extra 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?

Names the exact scenario ('choose between candidates you already have, for example zod vs valibot') and its alternative ('use recommend_repos to find candidates'). The when-to-use vs when-not distinction is explicit and actionable.

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 declare readOnlyHint and openWorldHint, but the description adds substantial context beyond them: the cost profile ('makes 3 GitHub searches plus npm/PyPI lookups for the shortlist'), hosted rate limits (50 free calls/day), an auth requirement (X-GitHub-Token header for unlimited use), and a local fallback (npx -y whichlib). It also discloses the scoring model and tier thresholds so the agent can interpret output.

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 purpose and routing, then cost/auth details. It is dense and runs long for a single block, but nearly every clause carries decision-relevant information (routing, cost, auth, scoring, tier interpretation), so the length is largely earned rather than 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, the description still covers the return shape (0-100 score with weighted sub-components, tier bands, one-line verdict, full breakdown) and the operational envelope (latency, rate limit, auth, local alternative). An agent has everything needed to call and interpret this 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 100%, so the schema already documents need, limit and language with examples and constraints. The description adds the notion that results are ranked by fit = score x relevance and that limit caps returned repos, but no syntax or format detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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?

Opens with a specific verb+resource+outcome: 'Find the best open-source library for a need before adding a dependency.' It explicitly distinguishes itself from the sibling compare_repos ('use compare_repos when you already have names'), so an agent can route without opening either 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 an explicit when-to-use ('when you do not yet have candidates') and the alternative with its trigger condition ('use compare_repos when you already have names'). The precondition of needing a plain-words need rather than a library name is also 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 only declare readOnly and openWorld, but the description goes far beyond: it discloses the exact scoring weights, tier thresholds, the underlying network calls (one GitHub search or one raw.githubusercontent download plus one npm/PyPI lookup per repo when withDownloads is true), rate limits (50 free calls/day), the auth mechanism (X-GitHub-Token header), and a local-run option. This is unusually rich behavioral context.

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 sibling exclusion are front-loaded, and most sentences carry distinct information. It is dense and long, with the full scoring breakdown arguably more than an agent needs to select the tool, so it is slightly over-full rather than maximally tight.

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?

No output schema exists, yet the description fully characterizes the return values (0-100 score, tier labels, one-line verdict, full breakdown), plus cost, latency, auth, and rate limits. Nothing an agent needs to call it correctly is missing.

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, and the description adds real meaning: 'risingRank keeps that order' and 'sorted by score (starsRank keeps the stars order)' explain the ordering consequences of period, and it clarifies that withDownloads trades speed for registry data. The parameter coverage is strong; only minor format detail is absent from the description vs. 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 (discover the most-starred GitHub repositories created in a time window, or period='rising' repos by weekly star gain), and explicitly distinguishes itself from recommend_repos. An agent can identify what this returns and how it differs from compare_repos/recommend_repos 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?

Explicitly names the alternative and the condition that selects it: "Not the right tool for picking a dependency... use recommend_repos for that," and it explains what each period value is for. Both when-to-use and when-not-to-use are covered.

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