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

Annotations declare this is a mutating but non-destructive tool. The description adds real consequence context beyond that ('a failed chain repair retains the stage and costs points') and signals that state goes stale after each call. However it never explains what a successful finish does, what 'points' are, or what 'inspect' returns, so the behavioral picture is only partly filled in.

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?

Four short sentences, front-loaded with the two actions before the constraints. No fluff, though the terseness borders on cryptic rather than efficient.

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?

For an 8-parameter mutating tool with three enums and no output schema, the description is thin. It does not explain half the parameters, the inspect return shape, or what completing a stage requires, so an agent cannot confidently invoke it without spelunking the schema.

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 50%, so the description must compensate, but it effectively adds meaning only for version ('Use the current version') and obliquely for test/choice. The evidence array and the verification enum (relevant/unrelated) — both likely central to finishing a stage — remain completely opaque.

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 gives loose verbs and nouns ('inspect one test', 'finish the current stage') but never names the resource (a diagnostic attempt) or clarifies what 'finish' entails. The title's 'repair' language conflicts with an action enum that only offers inspect/finish, leaving the tool's actual job ambiguous.

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?

'Use the current version' and 'Refresh after every action' are state-hygiene instructions, not routing guidance. Nothing says when to call this instead of morrowkin_read_diagnostic_attempt or morrowkin_start_diagnostic_attempt, nor when to choose inspect over finish.

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