inspect_mcdev_git_policy

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

With no annotations, the description carries the full burden and does so: read-only, no persistence, no branch/commit/history/auth/artifact reads, no native execution, ancestry based on a stale local remote-tracking snapshot, unknown remote BU synchronization, and non-atomic with a concurrency caveat. That is unusually rich disclosure of exactly the traits an agent needs before relying on results.

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?

It is front-loaded and every clause is arguably substantive, but the writing is a dense chain of negations and internal jargon ('top-level verified covers status metadata only; refs.verified is independent'), making it hard to parse on a first read. Tighter grouping of scope, limitations, and concurrency would improve it.

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?

Given no annotations, no output schema, and one parameter, the description supplies scope, non-goals, staleness of ancestry data, partial verification semantics, and concurrency constraints. What it still omits is any hint of the shape of the returned metadata beyond vague mentions of 'verified' and 'refs', which would help the agent interpret the output.

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?

There is a single required parameter with 100% schema description coverage ('Canonical absolute mcdev project root'), so the schema already does the work. The description adds no further meaning about workspaceRoot (e.g., what happens if it's not a Git repo or not canonical), which fits the baseline 3 for full schema coverage.

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 specific verb+resource: 'Read-only Git metadata inspection', and explicitly separates itself from inspect_mcdev_project's auth protection checks, so it's distinguishable from the nearest sibling. However, the purpose is buried inside a string of caveats rather than stated as a clean sentence about what Git metadata is returned (status, refs, ancestry), which keeps it below a 5.

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?

The description draws one boundary ('Separate from inspect_mcdev_project auth protection checks') and warns to avoid concurrent project/Git mutation, which implies when it's appropriate. But it never says positively when to call this tool, nor names alternatives like inspect_mcdev_git_range, which most agents would need to disambiguate between the two Git inspection siblings.

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