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

Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false), and the description adds real context on top: results depend on authentication (private repos only for owned/collaborated ones), the omitted-query behavior, and pagination semantics where `total` is the full match count rather than page size. These are behavioral facts an agent cannot get from the annotations or schema alone.

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 tight sentences, front-loaded with the search scope before the alternate listing mode and pagination caveat. The 'Mirrors GET /api/v2/search/repos' clause and stacked parentheticals add some density, but no sentence is 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 no output schema, the description usefully explains the `total` and `nextOffset` response fields, which covers the main pagination risk for a 4-parameter search tool. It stops short of describing the shape of each returned repository object, a minor remaining gap.

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 the baseline is 3, but the description adds meaning beyond it: `query` omission switches the tool from search to listing your repositories, and `nextOffset`/`total` semantics clarify how the offset parameter should be driven. Only the `sort` and `limit` parameters get nothing beyond their schema text.

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 repositories') plus the exact match fields (owner, name, owner/name, description) and case-insensitivity, and scopes results to 'every public repo, plus the private ones you own or collaborate on'. That scoping distinguishes it from the sibling code/issue/PR search tools without needing to name them.

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 an explicit alternate mode: omit `query` while authenticated to list your own repositories rather than search. It does not name any sibling tool (e.g. merjax_repo_search or merjax_semantic_search) as the alternative, so routing between the several search-ish siblings still requires inference.

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