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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses real behavior: AND semantics across query words, light stemming, exact-phrase priority, the shape of returned slugs and snippets, and packet fields (claim, passages, provenance, confidence, as_of). It also volunteers a privacy fact — queries are retained in a private usage log — which is exactly the kind of context annotations cannot convey. It stops short of stating result caps or latency, so not a 5.

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 corpus, then matching rules, then return shape, then caveats — a sensible ordering with dense but non-redundant sentences. The trailing privacy-log pointer is slightly tangential but does earn its place by flagging data retention; the SI/RSI note is a useful edge-case aside rather than filler.

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 and does describe returns (slugs with line snippets, up to 3 packets with named fields). With one simple required parameter and read-only annotations, nothing an agent needs to call this correctly — corpus, matching rules, output selection, retention — 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 description coverage is 0%, so the single 'query' parameter carries no documentation of its own, yet the description fully specifies its semantics: case-insensitive, every word must match title/tags/body, stemming, phrase boosting, and even an abbreviation expansion (SI / RSI). That is meaning genuinely absent from the schema, well above the 3 baseline for well-documented schemas.

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 with an explicit corpus scope: 'case-insensitive search across all notes, reference notes, library pages and the mission page.' That scope implicitly separates it from list_notes and read_note, but no sibling is named directly, and the relationship to ask (also a retrieval tool) is left for the agent to infer.

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?

'Prefer packets for injection' is guidance about which part of the result to consume, not about when to choose this tool over ask, list_notes, or related_notes. The agent can infer that this is the keyword-retrieval entry point, but there is no explicit when-to-use or when-not-to-use statement and no exclusion of the exhaustive-list sibling.

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