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

With no annotations provided, the description carries the full burden and delivers substantial behavioral disclosure: its AUTH requirement, server-side hash verification ('the server verifies its hash'), and side effect of publishing 'a dereferenceable copy.' This goes beyond the raw schema to communicate what actually happens on the server, though it stays silent on idempotency, reversibility, and retention of the published copy.

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 dense sentences, zero waste: the first states the action, the second details inputs and server behavior, and the third covers the optional case. Every clause earns its place without repetition.

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 6-parameter mutation with no output schema and no annotations, the description thoroughly covers the essential aspects: what triggers the call, what to supply, what the server does (hash verification, publication), and the optional successor feature. Minor gaps — error cases, reversibility, and how long the dereferenceable copy persists — keep it just short of complete.

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?

Despite only 33% schema description coverage (2/6 params), the description adds meaningfully beyond the schema: it disambiguates the relationship between preflight_receipt_string and preflight_receipt_hash ('verifies its hash'), documents successor_attempt_id ('Optionally point to a later replacement attempt' — which has no schema description), and references attempt_id. This compensates well for the low 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?

The description uses a specific verb+resource: 'close your open attempt without a measurement' with a clear trigger condition ('after a predeclared admissibility gate fires'). The purpose is clear and distinct from sibling get_*/submit_measurement tools. However, the heavy use of domain jargon ('predeclared admissibility gate', 'dereferenceable copy') and lack of explicit sibling comparison keeps it from 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 gives a clear conditional context for when to call this tool ('after a predeclared admissibility gate fires') and implies the alternative path via 'without a measurement.' However, it never names alternative tools, doesn't provide when-not-to-use scenarios, and leaves ambiguity about whether this handles all abort cases beyond gate failures.

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