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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the trailing 'Read-only.' adds nothing, but the description contributes substantial behavior beyond that: a shared probe across three surfaces, cache behavior, deterministic rule settlements with a `by` provenance field, per-file kinds, browser editability limits, and exact git commands. It does not cover auth requirements or rate limiting, so a 4 rather than 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?

Purpose is front-loaded and every clause carries information, but the body is a single ~130-word run-on sentence with stacked parentheticals and backticked fragments, which makes it slower to parse than it needs to be. Bullet-style separation of the status values, file kinds and hunks block would preserve the content at lower reading cost.

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 carries the full burden of describing returns, and it does so thoroughly: status vocabulary, mergeable flag, shas, settled-vs-unresolved file structure, provenance of settlements, file kinds, editability and drafts. For a five-parameter read tool of this complexity, nothing an agent needs before calling it is missing.

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 would be 3, but the description meaningfully enriches the `hunks` parameter by specifying the return shape it triggers (diff3 text labelled by branch name plus hunks with id/mine/base/main) and names the tool that consumes it. `fresh` is left to the schema, which does define it, so no penalty.

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?

Opens with a concrete framing ('What stands between a PR and a clean merge, as the merge gate, the PR page and the Conflicts tab see it') and then enumerates the exact payload: status, `mergeable`, base/head shas, ruleSettled files, unresolved files with kind, editability and drafts. It is clearly distinguished from `merjax_get_pr`, `merjax_pr_status_summary` and the resolve/propose/commit conflict siblings by naming the consumers and the conflict-specific fields.

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?

Usage is clearly implied and partly explicit: the tool is the diagnostic probe for merge blocking, and 'With hunks: true ... for merjax_resolve_pr_conflict' routes the agent to the sibling that consumes this output. It does not state when NOT to use it (e.g. versus `merjax_get_pr` or `merjax_pr_status_summary`), which keeps it below a 5.

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