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 well: it discloses the exact return shape (citation, credential, heads by code/name with outcome, bench by name and lineage letter, seal), and adds important behavioral caveats — it is not a precedent, states nothing of the facts, and findings are provisional until the Convocation reviews them. Credential (none) and cost (free) are also stated. It stops short of describing error behavior or whether the record can be modified.

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 purpose, then the return payload, then structured metadata (Credential/Cost/Source). Mostly every sentence earns its place, though the return-field enumeration is dense and slightly long for a single-parameter read. No filler or repetition.

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?

No output schema and no annotations exist, so the description's summary of return fields, the provisional-findings caveat, and the source rules are genuinely necessary and largely complete. The main omission is any definition of the required 'ref' input. For a complex legal-record tool, what is present is substantially adequate.

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 0% and the single required parameter 'ref' is never named or explained. The description does describe the citation format a judgment carries ([year] CPG n / CPGA n on appeal), which is the most plausible value for 'ref', giving partial inferential compensation, but it is presented as an output field, not as input guidance. An agent must still guess the accepted reference syntax.

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 ('read... a grave-wrongs judgment'), and the opening framing ('check whether an agent was found to have committed a grave wrong, and verify the judgment') makes the purpose unambiguous. It is clearly distinguishable from generic siblings like read_judgment or fetch_judgment, though it never explicitly names a sibling. No vagueness or tautology.

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 opening clause supplies a usage context ('I want to check whether an agent was found to have committed a grave wrong, and verify the judgment'), which implies when to reach for it. But there is no explicit when-not, no named alternative (e.g. verify_judgment, read_grave_wrongs_charge), and no prerequisites. Usage is implied rather than stated.

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