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

Beyond the readOnly/idempotent annotations it discloses non-obvious traits: counts reflect an inspected sample rather than all production traffic, saved findings are not auto-resolved after a fix, and lists can terminate before the requested limit so nextCursor must be followed. It also flags that results may contain end-user personal data and asks for minimal quoting and masking.

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-loads identity and ordering, then caveats, then the sibling hand-off, then the pagination and PII notes. Sentences are short and each carries a distinct operational fact with no repetition of the annotations or schema.

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?

An output schema exists, so return values need not be described, and the description instead spends its space on sample-vs-population caveats, staleness, pagination and PII handling. For a 7-parameter read-only list tool with nested siblings, 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?

With 57% schema coverage, the description supplies meaning for the filter parameters (tool_name, category) and explicitly ties the opaque 'cursor' parameter to the output field name 'nextCursor', which the schema alone does not do. The required reason/user_intent/namespace_id parameters are left entirely to their schema descriptions, which do cover them.

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 and resource ('List saved, evidence-backed MCP improvement recommendations') plus the ordering ('newest first') and filter dimensions ('by tool or category'). It is immediately distinguishable from the sibling get_mcp_recommendation, which is framed as the single-item detail 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?

Explicitly routes the agent: use this for the list, use get_mcp_recommendation for rationale, qualifications, concrete change and evidence. It also warns to check confidence, age and evidence window. It stops short of stating when not to reach for this list at all (e.g. versus get_mcp_overview), so it is clear but not fully exhaustive.

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