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

It adds real value beyond the annotations by disclosing the return payload (diffs, preservation warnings, approval digest), the pinned-revision guarantee, and the fact that it is free and owner-authenticated. But 'No external writes' sits in tension with destructiveHint=true and readOnlyHint=false, and the description neither reconciles that nor explains state it may leave behind; the idempotency story is also muddled, since the description is silent while the schema's idempotency_key implies retry safety that idempotentHint=false denies.

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, no filler, and the most decision-relevant fact (no external writes) is placed last as a clean safety signal while the return contents are front-loaded. Phrasing like 'Free owner-authenticated inspection' is slightly compressed but still readable.

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 does well to enumerate the return contents, but for a non-read-only, open-world, destructive-hinted tool the agent still lacks the missing pieces: what the approval digest is used for, what happens to the preparation afterwards, and which sibling to call next. The two undocumented required UUID parameters remain an unaddressed 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 description coverage is only 33% — server_id and github_connection carry no description, only UUID format/pattern — and the description contributes nothing about any of the three parameters. It doesn't explain what server_id scopes, what a github_connection represents, or how the approval digest relates to inputs, so the coverage gap is left unpatched.

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 is specific about what comes back: 'exact proposed file diffs, preservation warnings and approval digest' at a 'pinned GitHub revision', which tells an agent this is a dry-run patch preparation rather than an apply. However, it never names the action verb directly ('inspection' stands in for 'prepares a patch') and gives no signal to distinguish it from close siblings like get_repository_preparation or create_preparation_pull_request.

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?

There is no explicit when-to-use, when-not-to-use, or alternative naming, despite a crowded sibling set (check_repository, get_repository_preparation, create_preparation_pull_request) where the boundaries matter. The only implicit guidance is 'no external writes', from which an agent must infer that this is the pre-approval step before creating a PR.

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