Find outlier posts

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds the meaningful behavioral detail that results are relative to the caller's own median rather than absolute thresholds, but says nothing about the default lookback window, sorting, or the shape of the two returned groups.

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 with the core definition front-loaded and no redundancy. The closing clause is partly motivational rather than informational, but it is brief enough 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 analytical tool with no output schema and no annotations explaining semantics, the description should clarify the lookback window (posts) and how many results per side (top) are returned. It covers the comparison concept well but leaves the result shape and windowing behavior 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 description coverage is only 40%, but the description usefully expands the metric parameter far beyond the schema by listing eight named metrics, which the schema leaves as an undocumented plain string. It does not explain top (how many best/worst per side) or posts (the lookback window size), so coverage remains partial.

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 analysis operation on a specific resource: best and worst recent posts measured against the account's own median on a single metric, with the metric set enumerated. The median-baseline framing implicitly separates it from per-post tools like analyze_post and get_media_insights, though no sibling is named directly.

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?

'Shows what to repeat and what to drop' implies the strategic use case, and the schema's type field nudges toward comparing within one format. There is no explicit when-to-use/when-not guidance or pointer to an alternative tool for related analysis.

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