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

Annotations flag it as destructive, open-world, and non-idempotent, but the description adds substantial context beyond them: the exact state transition (draft to submitted), that a platform fee becomes a due charge, that a licensed attorney is engaged, that nothing is served or filed before attorney review, and the test-key vs live-key behavior difference. This is exactly the behavioral disclosure the annotations don't carry.

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 trigger condition ('Use this when...') followed by effects, key-mode nuance, and constraints. Dense and mostly waste-free, though the multiple clauses about attorney engagement and test/live keys make it lengthier than typical.

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?

Covers the trigger, side effects, key-mode behavior, auth requirement ('Needs the person's account: sign-in or an API key'), return value ('Returns the case and its check results'), and the next tool to call. With no output schema, this fully compensates.

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 both parameters are documented in the schema (baseline 3). The description reinforces confirmedByPerson semantics ('Confirm with the person first, then pass confirmedByPerson: true') and adds the important constraint that attestations must be the person's own statements, which goes beyond the schema. Marginal but real added value.

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 ('submitting a draft' of a case) and distinguishes itself from siblings by naming evictions_validate_case as the wrong tool for checking a draft. An agent can identify this as the submission/finalization step without opening the 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 explicit when-to-use ('the person has said yes to submitting a draft that passes every check') and when-not ('Do not use this to check a draft (use evictions_validate_case)'), naming the alternative. It also routes the agent to the follow-up tool evictions_list_case_charges.

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