Tolca: Québec contractor check

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

Annotations already declare read-only, idempotent, open-world and non-destructive behavior, so the bar is lower; the description still adds real value by naming the four sources queried, the 12-month contract window, and that extraction dates accompany the verdict. It does not mention latency, rate limits, or what happens when no source matches.

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?

Two sentences, both front-loaded with the key facts (sources first, then when-to-use and inputs). The first sentence is clause-dense, but no sentence is wasted or redundant.

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-value detail is not needed, and the description still summarizes the verdict model. Sources, trigger conditions, identifier options and freshness are all covered, which is complete for an agent deciding whether and how to call this multi-source lookup.

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, but the description adds a disjunction not expressed in the schema (zero required params): the caller must supply neq, licence or name. It does not explain acceptable name-matching fuzziness or the effect of lang, though the schema documents both.

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 (check) plus resource (Québec construction contractor) and enumerates the four data sources and their scope. It clearly differentiates itself from the sibling qc_licence by covering RBQ licence plus RENA, MELCCFP penalties and SEAO contracts in one call, and names the verdict values returned.

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 an explicit trigger ('Use when the user asks whether a Québec contractor, subcontractor or renovation company is licensed, trustworthy or eligible for public contracts') and tells the agent which identifier to supply. It does not state when to prefer the sibling qc_licence over this broader check, so the alternative-route guidance is incomplete.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-structured behavior: the result reflects current status ('right now', ACTIVE), which implies a live external lookup rather than a cached record, and enumerates the returned fields including the restriction flag.

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?

Four tight sentences with the core capability, return shape, batch hint, sibling exclusion and parameter guidance front-loaded in that order. No filler and nothing repeated from the schema or annotations.

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?

For a read-only lookup with an output schema, an alternative sibling and 100% parameter coverage, the description supplies everything needed: what it answers, what comes back, which identifier to pass, and when to prefer the other 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 100%, so the baseline would be 3. The closing 'Provide neq, licence or name' adds meaning the schema does not: despite zero required parameters, at least one identifier must be supplied, and any of the three is acceptable. That is useful disambiguation beyond the per-field descriptions, though it does not explain precedence when several are supplied.

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 ('does this Québec business hold an ACTIVE RBQ construction licence right now'), plus the exact return payload. It also names the sibling it is not for (RENA ban / environmental penalties), so an agent can distinguish it from qc_contractor_check without opening either schema.

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?

Explicitly routes the agent: use this for live RBQ licence status, use qc_contractor_check for the RENA public-contract ban and environmental penalties. It also flags the batch use case ('good for checking several contractors one after another'), which is exactly the kind of when-to-use context that is otherwise invisible.

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