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

Annotations only cover the read/write/idempotent profile; the description goes well beyond that with the authorization model, the required 'repo' scope, the side effect that a base change re-runs pull_request CI against the new base, the auto-merge disarming, and the fact that marking ready kicks off AI review. That is exactly the mutation-risk context an agent needs.

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?

Front-loaded with the purpose, then permission, then side effects, then return shape—a sensible order. The slash-and-parenthesis phrasing ('Title / body / base:', 'marking ready starts the AI review') is dense and slightly run-on, but nearly every clause carries information an agent would otherwise have to guess.

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 compensates by enumerating the returned fields, and it covers auth, side effects, and preconditions for a mutation tool. The only shortfall is that it never mentions the head-branch-update sibling, so an agent must infer that base changes here differ from merjax_update_pr_branch.

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 schema already carries baseline meaning; the description still adds consequence-level semantics the schema lacks—what changing 'base' triggers and what the 'draft' flag does beyond toggling state. It adds little for owner/repo/number, but those are self-evident and schema-documented.

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 (edit) plus the exact editable fields (title, body, base branch, draft state) on a named resource (pull request). It also disambiguates the draft path by naming merjax_set_pr_draft and the base path by restricting to open PRs, so an agent can separate this from siblings without opening a schema.

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 concrete preconditions—'repo' scope, author-or-write-access for title/body/base, the stricter rule for draft, and open-PRs-only for base changes. It does not say when to prefer the dedicated merjax_set_pr_draft sibling over this tool's draft parameter, leaving one real routing ambiguity.

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