search_org

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

With no annotations, the description carries the burden and does disclose meaningful behavior: nothing is cloned, search runs remotely against the org's GitHub/GitLab repos, and the terms are executed concurrently ('each is one search, run at once'). It omits auth requirements, result caps per term, and rate limits, which keeps it short of a 5.

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 purpose is front-loaded and the length is reasonable, but the long run-on sentence with a chain of parenthetical examples ('what reads a metric, env var, header, queue or secret') is dense and harder to parse than a short bulleted breakdown would be. Some example clauses repeat the same idea.

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 needn't be explained, and the description covers the key semantics: remote-only search, literal terms, parallel execution, and the follow-up read_org_file. Remaining gaps are operational (auth, per-term result limits, pagination) rather than about how to invoke the tool.

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 0%, so the description must compensate and largely does: terms is defined as 1-4 literal strings with a worked example and the concurrency rule, and org is scoped by the 'several orgs configured' condition. It still doesn't say what shape the org value takes (slug vs display name) or what happens if more than 4 terms are passed.

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 names the resource (the org's repos on GitHub/GitLab, not cloned) and the operation (find where code uses a literal term), with concrete examples like templates importing exports or the readers of a metric/env var/secret. It is specific and clearly distinct from on-disk search, though the opening phrase 'Where the org's code uses something' is oblique before the clarifying clauses arrive.

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?

It gives concrete use cases and an explicit next step ('Then read_org_file(repo, path)'), and it states when to set org ('only when several orgs are configured'). It never explicitly names a sibling alternative such as find_across for local search, so the routing guidance is clear but not fully comparative.

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