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

Without relying on annotations, the description adds genuinely useful behavioral guarantees: output is deterministic, citations are attached, missing datapoints are surfaced as explicit gaps, and nothing is fabricated. What it omits is whether the compiled draft is persisted and what request_id/payment_ref imply (annotations mark it non-readOnly, non-idempotent), so side-effect behavior is left unclear.

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?

Three tight sentences with the core action front-loaded and the anti-fabrication contract second; no filler. Slight redundancy in restating the source inputs that are visible in the schema keeps it from a 5.

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 values need not be described, but for a 6-parameter tool with nested objects and 0% schema coverage the definition leaves too much unexplained - notably the payment_ref/request_id mechanics and whether the draft is stored. Those gaps matter given readOnlyHint=false and idempotentHint=false.

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 0% across 6 parameters including nested objects, so the description must compensate and largely does not. It only gestures at company_facts and ghg_result; framework, options, request_id, and payment_ref are never explained, and 'framework' would benefit from pointing at get_framework or list_frameworks.

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 artifact: 'Compile a deterministic, cited disclosure draft' from company facts plus an optional verified GHG-ledger result. That is distinct from every sibling (get_framework, list_frameworks, verify_result, describe_agent), so an agent can route here without opening the 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?

Usage is implied by the input mention ('from supplied company facts and an optional verified GHG-ledger result'), which suggests verify_result should run first for the GHG part, but that is never stated. There is no explicit when-not and no named alternative, so the routing is inferential rather than directive.

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