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

Goes far beyond the annotations: it discloses that document is hashed into build_ref, that a task_completions row and a signed receipt are minted, that the completion releases the next held seat and feeds the fan-out synthesizer/rollup, and that failed runs store nothing. It also states the required permission and the 404/not_live refusal conditions, none of which are derivable from readOnlyHint/idempotentHint/destructiveHint.

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 action and endpoint, and each subsequent clause carries distinct information (storage, hashing, receipt, fan-out side effects, auth, failures). The prose is dense with run-on parentheticals and emphasis, which slightly hurts readability but wastes little.

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 a mutation tool with no output schema, the description covers the side effects, the authorization requirement, the failure semantics, and points to tascan_get_receipt for the returned artifact. Nothing an agent needs to invoke it correctly appears missing.

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 baseline would be 3, but the description adds real meaning: it stresses that document IS the hashed deliverable ('send the real content, not a summary') and clarifies verification becomes the seat's second artifact_path. The cost_micro_usd default rationale is left to the schema.

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+resource ('Finish a claimed local run') plus the underlying endpoint (POST /runs/:run_id/finish), and its two outcome branches are fully spelled out. An agent can distinguish this from tascan_claim_run or tascan_heartbeat_run without opening any 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 clear context for each outcome: 'completed' stores artifacts and mints a receipt, 'failed' finishes with error text and stores nothing, and it names a prerequisite (requires agent:dispatch:code) and refusal cases (404 / not_live). It never explicitly names tascan_claim_run or heartbeat_run as the alternative operations, so the when-not guidance is inferred rather than stated.

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