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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), and the description adds real behavioral depth beyond them: the statute-then-provision-link search flow, deduplication by SAOS ID, the conditional dependency on server-side Cohere configuration, and the cap on fetched excerpts. That is meaningfully more than the annotations disclose.

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 core purpose, then layered caveats in an efficient order (pipeline, stage choice, reranker condition, follow-up). The embedded indentation and backtick formatting are artifacts of source docs but the prose itself is tight.

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 values need not be described, and the pipeline/caveats are well covered. However, for a 9-parameter tool with 0% schema description coverage, six tuning knobs remain unexplained, leaving an agent without guidance on how to shape result size or cost.

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 description coverage is 0% across 9 parameters, so the description carries the full burden. It explains 'rerank' and 'rerank_fetch_limit' clearly, but leaves candidate_limit, provision_limit, context_max_chars, case_text_max_chars, cases_per_provision, and rerank_result_limit entirely undefined in both places.

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 ('Discover related-case candidates') plus the input type (natural-language legal issue), and sketches the internal pipeline. It does not, however, distinguish itself from the sibling tool 'related_cases', which an agent could easily confuse it with.

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 stage selection guidance (rerank=false is the inexpensive discovery stage; rerank=true reranks only when a Cohere reranker is configured) and a clear follow-up directive to call get_case for every judgment used. No explicit when-not-to-use rule against 'related_cases' or 'search_case_by_signature', so it stops short of a 5.

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