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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the burden is lower. The description still adds real value by disclosing result ordering ("newest first") and the returned fields (company, date, type, value, parties, roles), which annotations do not carry.

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, zero filler: the first carries all filter dimensions, the second carries return shape and ordering. It is front-loaded on the action and sized appropriately for a 14-parameter tool.

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 usefully spells out the return payload and ordering, which is the biggest gap it had to fill. It leaves pagination and total-result behaviour to the schema, which handles page/limit adequately, but says nothing about result-set size limits or empty-result semantics for a search tool this broad.

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 100% and every parameter carries a detailed schema description, including the subtle firm-state vs company distinction and the disclosed-value caveat. The description restates the filter axes at a high level ("the disclosed value and the year") without adding syntax or edge-case information beyond the schema, so baseline 3 applies.

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 ("Find deals in the Corridome register") and enumerates every filter axis, so the agent knows exactly what dimension set this tool spans. It does not name a sibling, so it never explicitly says why this rather than get_deal or search_firms, but the multi-filter framing makes the distinction inferable.

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 filter list ("by company name, by a firm and its role and side..."), which tells an agent how to narrow results, but there is no explicit when-to-use, when-not-to-use, or alternative named. Nothing tells the agent to prefer get_deal when it already has an identifier.

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