record_publication

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

With no annotations, the description carries the behavioral transparency burden. It discloses two important non-behaviors: it never publishes and does not infer live state from a payload. However, it does not mention side effects, idempotency, overwrite behavior, whether stale revision data is rejected, or what happens on conflicting information. The negative guarantees are useful but incomplete.

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 description is two short sentences with no wasted words. The primary action is front-loaded, and the clarifying non-behaviors follow immediately. It is appropriately sized for what it attempts to convey.

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?

This is a 14-parameter tool with no annotations, no output schema, and no per-parameter documentation. The description gives only high-level framing and negative guarantees. The agent is left without guidance on required fields like expected_revision and status, optional relationship between fields, and expected behavior for statuses such as 'missing' or 'trashed'. The description is not sufficient to safely invoke this tool correctly.

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 0%, and the description does not explain any of the 14 parameters. The phrase 'verified' and 'does not infer live state' provides indirect context that fields like status, expected_revision, and verification-related fields are caller-supplied and trusted as-is, but this does not compensate for the lack of parameter-level guidance. Because the description adds only general context, not specific parameter semantics, it remains a weak performance on this dimension.

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 a clear verb and resource: 'Record a verified WordPress outcome.' The added statement 'This tool never publishes and does not infer live state from a payload' helps distinguish it from siblings like compare_payload_to_live_state and clarifies that the name does not imply a publishing action. However, 'outcome' remains somewhat generic, and the exact scope of what counts as an outcome is not defined.

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 implies the tool should be used when recording an already-verified WordPress outcome, and explicitly says it is not for publishing or inferring live state. It does not explicitly state when alternatives should be chosen, nor does it name any sibling tools. Usage context is present but mostly implicit.

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