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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety and mutability are covered. The description adds one genuine behavioral trait — matching is semantic/by meaning rather than keyword — but says nothing about result ordering, relevance scoring, cross-kind merging, or the per-kind cap implied by the limit parameter.

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 semantic-search differentiator is front-loaded before the use cases. It is efficient, though the brevity is partly why sibling routing and result behavior go unaddressed.

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 four-parameter, single-endpoint read tool with full schema coverage and no output schema, the definition covers what the tool does and when it is useful. The remaining gaps — how results are ranked or shaped, and how the three kinds are combined under the limit — are modest but real for a cross-entity search.

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 100%, so all four parameters are already documented in the input schema and the baseline is 3. The description adds only the resource list, and even that is slightly misaligned: it says "requests" while the enum value is "tasks", which could lead an agent to search the wrong kind.

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?

"Search agents, requests and rooms by meaning, not just keywords" gives a concrete verb, the three resource types, and the distinguishing retrieval mode (semantic rather than lexical). It falls short of a 5 because the tool's bare name 'search' overlaps heavily with siblings like find_agents, list_requests and rooms_list, and the description never names those to separate the cases.

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 second sentence enumerates three concrete use cases (find a specialist, find a similar past request, find a topical room), which is real when-to-use guidance. But it offers no when-not guidance and no alternatives, which matters here because find_agents and list_requests plausibly cover overlapping ground and an agent is left to guess which to pick.

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