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

Annotations already cover read-only, idempotent, non-destructive, and closed-world, so the bar is lower, yet the description still adds real substance: scores are 0–100 ranking signals rather than probabilities, comparisons are scoped to one platform/account/metric/age cohort, an idea's own wins are excluded, and semantic evidence warms asynchronously with semanticStatus reporting it. The closing 'This is read-only' merely repeats readOnlyHint and earns nothing, but the rest is genuinely useful 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 crucial score-semantics caveat are front-loaded, and each subsequent sentence adds a distinct fact about cohort scoping, exclusions, or semantic readiness. It is dense but not padded; the trailing 'This is read-only' is the only sentence that fails to earn 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 five-parameter read-only ranking tool with an output schema, the description covers intent, score interpretation, cohort fairness, async evidence state, and safety. Given the output schema documents the return shape, the mention of platform evidence, confidence, and sourceTruncated is supplementary rather than missing; only the enum-level filter semantics remain unexplained.

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 the burden; it does name the filter dimensions (provider, level, used-status) and 'bounded pagination', which covers all five parameters at a high level. However it adds no meaning to the enum values themselves — nothing explains what 'needs_data' means versus 'neutral' in levels, or what the used-status filter changes — and it calls the parameter 'level' singular while the schema uses a multi-value 'levels' array.

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 opening sentence gives a specific verb and resource — 'Ranks active workspace ideas by historical potential' — plus the optional filter set and pagination. It implicitly separates itself from list_ideas (raw listing) and get_idea_performance (per-idea metrics) by emphasizing ranking across ideas, but it never names a sibling explicitly.

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 only implied: an agent can infer this is the tool for prioritized browsing of ideas when filter/sort by potential is needed. There is no explicit when-to-use statement, no when-not-to-use, and no routing to list_ideas or get_idea_performance for adjacent needs.

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