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

Goes well beyond the annotations: it discloses the error contract ('never raises a protocol error; it returns {"error": ...}') with an example, states retry safety after correction, and warns that clocks running off an earlier submission are estimates until actual times are passed in 'submitted'. These are behavioral traits the readOnly/idempotent hints do not convey.

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-loads purpose, then a worked input/return example, then regime-specific parameter notes, then the exclusion and error contract. The return-value fragment partially duplicates the output schema, but the call shape is otherwise dense and waste-free.

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?

An output schema exists, so return explanation is not required, and the description still supplies the error path, retry safety, and per-regime prerequisites. For a 12-parameter, nested-object tool this is enough to call correctly on the first attempt.

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 baseline is 3, but the description adds genuine cross-parameter semantics the schema cannot express: which regime requires which extra parameter (DORA needs classification_at + country, SEC needs materiality_determined_at, HIPAA takes discovery_date and flags.individuals_affected) and how 'submitted' changes computed results. It leaves entity_class, subdiv, and measure_available_at to the schema, which lower-usage params can tolerate.

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 and resource ('Compute every reporting deadline of one regime from the moment of awareness') with explicit scope ('one regime'). It also names the sibling it is not for ('Not for several regimes at once: use compute_deadlines_multi'), so an agent can distinguish it 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 a concrete triggering condition ('when an incident has just been identified and the agent needs the instants'), an explicit exclusion, and the named alternative for the excluded case. Usage is fully determined, not inferred.

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