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

The description contradicts the annotations: it says to 'record', 'persist', and 'store' a prediction document, implying a state-changing write operation, while annotations declare readOnlyHint=true. This is a serious inconsistency that would mislead an agent about the tool's side effects. The added notes about no validation and no deduplication are useful but cannot overcome the contradiction.

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 well-structured with explicit sections and front-loaded purpose. It is slightly repetitive ('Call once...' and 'Call exactly once') but every section adds usable guidance. Overall it is concise for the amount of context it provides.

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 one-parameter tool with a rich schema and output schema, the description covers usage, limitations, and parameter semantics well. However, the contradiction with the readOnlyHint annotation creates unresolved confusion about whether the operation mutates state, and the description does not clarify the discrepancy. This prevents the definition from being fully 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?

Schema coverage is 100%, so the schema already documents the single parameter. The description adds meaningful nuance beyond the schema: the prediction should be the exact machine-readable document, and the human-readable report is deliberately separate. This helps the agent understand what value to place in the parameter.

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 states a specific verb ('record'), a specific resource ('complete structured prediction document'), and a clear purpose ('for downstream evaluation'). It also separates this tool from caller-facing marketplace tools and names a sibling alternative, so an agent can distinguish it from the large sibling list.

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 explicit when-to-use guidance ('at the end of a scheduled analysis run'), the exact call pattern ('exactly once', 'never partially or repeatedly'), and a stated alternative ('get_datetime'). It also clarifies the tool's intended internal role.

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