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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered; the description adds a genuinely useful failure-mode guarantee that an agent could not infer — unreachable sources are reported as unavailable rather than as zero results, preventing false negatives. It stops short of describing result ordering or how mixed-source rows are merged, which is the only remaining gap.

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?

Three short sentences, each doing distinct work: positive scope, explicit exclusion with alternative, then a failure-mode caveat. Scope is front-loaded and there is no filler.

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 3 params at full schema coverage, no output schema, and annotations carrying the safety profile, the description covers scope, exclusion, and error semantics well. The one thing an agent might still wonder — whether results are interleaved across sources or returned per type — is only obliquely implied by the schema's "rows across all sources" wording.

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 coverage is 100%, so query, types, and limit are already documented with defaults and bounds in the schema itself. The description reinforces what is searched (name and description) but adds no syntax, format, or combinatorial guidance beyond the structured fields, so the baseline 3 applies.

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 (search) and an explicit resource scope: projects plus the public catalogue (templates, skills, gallery), matching by name and description. It immediately distinguishes itself from the closest sibling by naming search_project_code as the tool for file contents.

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?

Provides an explicit negative condition ("Does NOT search inside project files") paired with the named alternative to use instead, which is exactly the routing signal an agent needs. The catalogue-vs-project scope plus the types parameter give a complete picture of when this tool is the right pick.

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