search_canon

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description still adds real value beyond them: the ranking engine (FTS5/BM25), CJK bigram tokenization, and the important recall caveat that a miss does not prove absence. It omits result shape and whether the search is scoped by campaign.

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 sentences, no filler, and the core capability is front-loaded before the usage caveat. Every clause carries information an agent can act on.

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 should describe what a hit contains and how limit bounds results; instead it only implies hits are readable. The safety profile is fully carried by annotations, so the remaining gaps are the undocumented parameters and undefined return shape — adequate but incomplete for a search 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 0% across three parameters, so the description carries the full burden and largely fails it: query, campaign_id, and limit (default 4, max 8) are never explained. Only 'CJK bigrams' indirectly hints at how the query string is tokenized; the scoping role of campaign_id and the cap on limit are left undocumented.

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 ('Search local canon') plus the retrieval mechanism (FTS5/BM25, CJK bigrams), which distinguishes it from siblings like read_canon and get_knowledge. It does not name an alternative explicitly, but the ranking-based full-text framing is enough for an agent to tell it apart from direct-read tools.

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?

'Read hits before citing; a miss is not proof of absence' guides how to interpret and act on results, which is useful workflow context. However, it never states when to choose this tool over read_canon, get_knowledge, or read_history, so the alternative-selection guidance is only implied.

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