search_docs

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description adds the useful scoping behavior that all_relevant excludes unrelated projects, but omits result ranking, top_k default behavior, and how product/version filters interact.

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 short sentences with the scope constraint front-loaded and no filler. 'Documentary evidence' is slightly jargonistic but the text is efficiently sized for the schema.

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?

An output schema exists, so return values need not be described. But with 7 parameters at 0% schema coverage and many enum values left unexplained, the description does not supply enough for an agent to filter confidently across product/version/project.

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 7 parameters, so the description carries the burden and largely fails to. It only illuminates the all_relevant value of source_scope and says nothing about query, top_k, product, version, project_id, or document_types.

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?

Uses a specific verb ('Retrieve') and resource ('documentary evidence') and scopes it to official BMC knowledge plus the effective project, which no sibling (list_projects, get_section, etc.) duplicates. However, it never names the tool as a ranked search or explains what a query actually returns, leaving the retrieval mechanism implicit.

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 only guidance is a narrow caveat that 'all_relevant never searches unrelated projects', which clarifies one enum value rather than when to choose this tool over siblings. There is no explicit when-to-use, when-not-to-use, or alternative named.

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