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

With no annotations provided, the description carries full burden. It discloses the search behavior (semantic, based on embeddings), scope mechanics (e.g., 'engineering-projected vector'), and run attribution. It also states 'a text-similar non-engineering claim never leaks in', adding confidence. However, it does not explicitly state that the tool is read-only (no side effects), which would be beneficial for a mutation-averse agent.

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?

The description is a single dense paragraph, but every sentence adds value. It could be broken into separate sentences or bullet points for easier parsing, but it remains concise and informative without redundancy.

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?

Given 7 parameters and no output schema, the description covers return fields (claim ids, similarity scores, text snippet) and explains the two scopes thoroughly. It also covers run_id usage. It does not explain 'engineering-projected vector' nor the '§7.6 identity-canonical' in detail, but these are domain-specific terms that may be assumed. Overall, it provides sufficient context for an agent to invoke the tool correctly.

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 71% (5 of 7 params have descriptions in schema). The description adds meaning beyond schema for 'scope' (explains default and detailed behavior) and 'run_id' (context about attribution and run-anchored property). For 'collapse_same_as', it clarifies the representative selection. The remaining params (limit, query) are simple types and schema descriptions suffice.

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 description clearly states it performs semantic search over methodist-published claims, distinguishes two scopes (scientific vs engineering), and specifies return fields (claim ids, similarity scores, text snippet). This differentiates it from sibling tools like 'methodist_search' or 'search_semantic'.

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?

The description explains when to use scientific scope (default, §7 claim space) vs engineering scope (reuse-discovery) and provides context for run_id attribution. However, it lacks explicit guidance on when NOT to use this tool versus alternatives like 'methodist_find' or 'explore_topic', so it's not a full replacement for sibling differentiation.

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