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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantive behavior beyond them: a revoked/reserved number returns status 'revoked_or_reserved' instead of a not-found error, only Judicial Council-adopted text is included, and prior-edition coverage is bounded rather than archival. That is exactly the kind of edge-case disclosure an agent needs.

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?

A single dense paragraph but front-loaded: the verb, resource, and examples come first, then returns, edge cases, exclusions, and the optional edition. Every sentence carries information, though the return-contents enumeration could be trimmed for tightness.

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?

With no output schema, the description carries the return-value burden and does so concretely (instruction text, Directions for Use, Sources and Authority, Secondary Sources, revision history). Edge cases, edition semantics, and non-coverage are all addressed, so nothing material is missing for a keyless lookup tool.

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 already 100%, so baseline 3 applies, but the description adds real meaning: `edition` is for trials conducted under an older instruction and only works where a delta exists (with a pointer to ca_ji_editions), and `number` also accepts verdict forms. It stops short of documenting parsing edge cases for the accepted number formats.

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+resource ('Get the OFFICIAL text of a California Civil Jury Instruction (CACI) by number') with concrete identifier examples (303, VF-303). It scopes itself to civil/adopted instructions, which implicitly separates it from the criminal calcrim_lookup and from the search sibling ca_ji_search.

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 use cases ('what is the official jury instruction for breach of contract', checking elements/Sources and Authority) and explicit exclusions (proposed revisions open for public comment are not covered; prior-year editions limited to baked deltas). It routes the agent to ca_ji_editions to check availability before passing `edition`.

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