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

The description declares 'Read-only' while the annotations set readOnlyHint=false, a direct conflict over the safety profile. Useful extras exist (cost of 3 MESH/call, and the caveat that green CI does not mean merged or deployed), but a contradictory safety claim on a mutation-permitted tool is disqualifying for this dimension.

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?

The text is short but built from em-dash fragments and parenthetical metadata '(3 MESH/call, a tool · ops)' that read like internal notes. Key information (read-only claim, caveat) is buried mid-sentence rather than front-loaded, and phrasing such as 'Checks tests live' is not self-explanatory.

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, no nested parameter documentation, and conflicting safety annotations, the description should carry the burden; instead it omits what a result looks like, what 'conflicts' means, and how 'equivalent proof' is supplied. The one substantive note — that green CI doesn't imply merged or deployed — is helpful but insufficient.

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 nominally 100%, but the sole parameter is a generic 'input' object whose schema text only shows examples for other tools (agent-brain, agent-memory). The description adds nothing about what to pass for this tool specifically, so the agent is left without usable parameter meaning.

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 names a recognizable goal — verifying that tests actually pass (CI status, test counts, scan result, conflicts) — but phrases it as cryptic fragments like 'Checks tests live' and 'the equivalent proof where there is no code surface'. An agent can roughly infer the intent, yet the verb+resource pairing is loose and it is not differentiated from siblings such as claim-vs-evidence-checker or deploy-live-check.

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?

No explicit when-to-use or when-not-to-use guidance is given; only an oblique hint that it applies where a code surface exists or 'the equivalent proof' does not. There is no routing toward alternatives like claim-vs-evidence-checker or deploy-live-check, leaving the agent to guess.

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