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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), but the description adds real disclosure beyond them: the corpus is the community version only, results are verbatim clauses with cite keys, and queries are retained 30 days without attribution. That retention/audit fact is exactly the kind of thing an agent cannot get from annotations or schema.

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 purpose, then when-to-call, then return shape, then the retention note. Four short paragraphs, each earning its place. The privacy sentence is slightly off-task for tool selection but is genuinely decision-relevant for some agents.

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 an output schema and full parameter coverage, the description only needs purpose, timing and behavioral caveats — all present. Minor gaps: no statement about what happens with zero matches or whether the limit truncates ranked results.

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 100%, so lang, laws, as_of, limit and include_explanatory are already well documented. The description adds nothing parameter-specific — the mention of the returned clause with document and version is output framing, not input semantics. Baseline 3 applies.

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 ('Search the privacy law') and scopes the corpus ('this community version holds'), which separates it from get_clause/get_document/list_documents by implying retrieval-by-query rather than by identifier. It stops short of naming any sibling explicitly, so an agent must infer the boundary from the verb alone.

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 concrete triggering conditions: call before writing or changing code that touches personal data, and before answering questions about legal requirements. No exclusions or named alternatives are offered, so the agent is not told when to use get_clause or get_document instead.

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