Calculate from discovered supplier facts

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds real value beyond that: 409 on stale identities, 503 on unavailable reviewed sources, 'stateless and public; no key, stored records, sent notices or filed liens', plus the note that only calculated outcomes carry deadline dates while review candidates stay unresolved.

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?

Five tight sentences, front-loaded with the core action, then return semantics, then error behavior, then the safety/hosting profile. No filler, though the error-code sentence is listy and could be folded slightly tighter.

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?

No output schema exists, so the description must carry return-value burden, and it does: independent notice and lien outcomes, sources, an exact nested input echo, and the calculated-vs-review distinction. Combined with the error codes, an agent has enough to call and interpret it, though the meaning of 'review candidates' is left implicit.

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 67% and the nested objects (events, rules_source, questions_identity) are largely documented in the schema itself. The description adds behavioral meaning to the identity params ('exact discovered' values, stale ones 409) and clarifies the output rule for events, but contributes little on syntax or format beyond what the schema provides. Baseline 3 fits.

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: evaluates supplier-events-v3 project facts against discovered rules and question identities to produce notice and lien outcomes. Clear about what it does, but it never distinguishes itself from the sibling calculate_supplier_deadlines (the non-v3 variant), so an agent cannot tell from the text which calculator to pick.

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?

Usage is only implied: the repeated emphasis on 'discovered' rule and question identities signals this must run after a discovery step (get_supplier_questions / get_state_lien_guide), but no explicit when-to-use, when-not, or sibling comparison is given. The workflow ordering is inferable but not stated.

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