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

Even with readOnlyHint and idempotentHint already present, the description discloses substantial non-obvious behavior: passages must be quoted verbatim and never paraphrased, tables return the whole table, currency fields may indicate multiple versions, dual-version sections expose version/other_version, and no-match has caveats. This far exceeds what annotations convey.

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 description is lengthy but every sentence carries operational weight: exact quoting, citation fields, heading path, versioning, tables, and no-match behavior. The most important usage directive is front-loaded, and the density is justified by the complete absence of an output schema.

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 must explain the return shape itself, and it does: verbatim, canonical_citation, heading_path, offset, currency, version, other_version, and table. It also covers edge cases like table matches and dual versions. An agent has enough information to invoke the tool and interpret its results correctly.

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 only 33%, so the description must compensate. It does richly for the key parameter, terms: '1-6 short words or phrases in the regulator's vocabulary' with abbreviations expanded, and clarifies obligation_id as referring to 'one obligation (section).' It does not mention max_passages at all, though the schema's min/max limits make its role partially inferable.

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 opens with a specific verb-plus-resource statement: 'Return ONLY the verbatim paragraphs of one obligation (section) that contain your terms.' It also distinguishes itself from get_obligation by positioning this as the fast route to specific requirements, so an agent can clearly tell this search tool apart from the full-section reading tool.

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 states when to use this tool ('fast way to get specific requirements out of a long section, instead of paging through it with get_obligation') and gives the negative case under which the tool is not conclusive: 'No match does not mean the rule is silent -- try other terms or read the section.' This is explicit routing guidance.

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