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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description layers on material economics and behavior beyond them: 'PAID, per call' and 'You are not charged when nothing matches'. It also discloses the return shape (source, URL, jurisdiction, VERIFIED/RESEARCHED label, EN/FR text) and a liability caveat ('Legal information, not legal advice').

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 pricing warning is front-loaded in the first two words, and the paragraph moves purpose → inputs → outputs → caveats in a sensible order. It is dense and clause-heavy in the middle (the corpus topic list and return-field enumeration), but essentially every clause carries information an agent needs.

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 only two required parameters, no output schema, and rich annotations, the description fills exactly the gaps that remain: cost model, partial-match billing, the provincial-vs-federal resolution rule, result fields, and topical coverage limits. Nothing an agent needs in order to call this correctly and interpret the response is missing.

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 100%, so the baseline is 3; the description earns above that by explaining behavior the enum cannot: AB, BC, ON, and QC get provincial lines while any other code silently degrades to federal-only results. That is real semantic value an agent could not infer from the 13-value enum, though it adds nothing on the question parameter beyond the schema.

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 names a specific verb and resource ('look up Canadian legal information by province') and enumerates the corpus topics covered (tenancy, employment, small claims, etc.), which makes it clearly distinct from the weather, recall, and earthquake siblings. It never names the one genuinely overlapping sibling, get_federal_law_section, so the boundary against statutory-section lookup is left implicit.

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 gives clear operating context: send a plain-words question plus a province code, and it states explicit exclusions ('Appeals and family law are not covered'), which prevents wasted paid calls. It stops short of routing the agent to an alternative tool for those excluded topics, so there is no when-to-use-instead guidance.

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