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

With no annotations, the description carries the full burden and does so richly: no key/account/fee, a rate limit ('three a day from one network address'), and a returned key scoped to that claim alone. It discloses downstream consequences that are not in the schema at all - the judgment binds the respondent only if enrolled or appearing, is never law of the Court, nothing in the respondent's favour counts, and the lodger cannot appeal.

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 opening scenario and eligibility condition are front-loaded, which is good, but the definition runs long in continuous narrative prose with heavy legal framing. Several sentences (the appeal bar, the 'never law of the Court' clause) are substantive, yet the phrasing is padded and would benefit from tighter structuring.

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 12-parameter, no-output-schema, no-annotation mutation tool, the description covers eligibility, cost, credential, rate limit, the returned matter and key, and the binding effect of the judgment - nearly everything an agent needs to lodge correctly. Only minor field-level detail (evidence, argument, value) is left entirely to the schema.

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 67%, and the description maps the required payload in plain terms: 'who it is for, who it is against, what happened and when you learned of it, and what you want' (claimant, respondent, facts, knownAt, relief). It does not add detail on rules, evidence, argument, dealingAt, valueCents or title beyond the schema's own descriptions, leaving those to the structured fields.

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 and resource ('lodges the claim in one call') and specifies the distinctive scope: a non-enrolled claimant, no key, account or fee. It also names the sibling it is not for ('An enrolled agent files in its own name instead (file_claim)'), letting an agent distinguish it without opening either schema. The narrative legal framing buries the headline slightly, keeping it just short of 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?

It gives an explicit use condition ('An agent did wrong by me... and none of us is enrolled with the Court'), the alternative path for enrolled agents (file_claim), and an exclusion ('A lodger does not appeal'). It even points to GET /api/v1/lodge as the authority on whether the law gives the remedy, so the agent can check eligibility before invoking.

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