search_entities

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

No annotations are present, so the description carries the full burden. It usefully discloses that only 'Confirmed' entities are returned, which tells the agent that candidate or proposed entities are excluded. However, it says nothing about result ordering, pagination beyond 'limit', match semantics (substring vs fuzzy), or permissions; the output schema covers return shape, but search behavior remains underspecified.

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 core action is front-loaded in the first sentence, followed by a scenario tip and then a compact per-parameter list. Nothing is padded, though 'query: search text' and 'limit: max results' restate the parameter names with little added information.

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 three-parameter search tool with an output schema (so return values need not be explained), the definition covers all parameters, gives a usage strategy, and flags the confirmed-entity scope. Remaining gaps — match semantics, default limit behavior, and how results are ordered — are minor for a search primitive.

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 description must document all three parameters, and it does: query as search text, entity_type as an optional type filter with concrete example values (capability, process, application), and limit as max results. The entity_type examples are the most valuable addition, hinting at the accepted vocabulary. It does not explain matching behavior for query or the effect of the empty-string default for entity_type, so it is good but not exhaustive.

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 Confirmed map entities by name/description'), which separates it from search_docs and search_evidence by naming the object being searched. The 'Confirmed' qualifier also implies a scope restriction. It stops short of explicitly contrasting with sibling entity tools like get_entity or search_evidence, so it is clear but not fully differentiated.

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?

Gives concrete when-to-use guidance for 'landscape questions' and prescribes a strategy: search capability/process types first, then follow relationships to applications. That is actionable context beyond a generic description. It does not name an alternative sibling or state exclusions (e.g., use search_docs for documents), which keeps it short of a 5.

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