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

With no annotations, the description carries the full burden and does well: it discloses that this is a retrieval operation and details the returned attributes (before/after values, detection timestamp, confidence, evidence). It does not discuss sorting, pagination, or empty-result behavior, but the read-only nature is clear from 'retrieve.'

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 tight sentences: the first packs the full behavioral scope and returned fields, and the second provides a crisp user-oriented summary. Every phrase contributes, with no filler or redundancy.

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?

The definition is complete enough for a simple read tool: input parameters are fully covered by the schemawatermark, and the description explains what results contain. Minor gaps remain around result ordering/pagination and behavior when no changes exist, so it is not a perfect 5.

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%, so the description need not repeat parameter details. It adds no new meaning about limit or since beyond the schema, keeping this at the baseline appropriate for fully documented parameters.

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 ('Retrieve observed changes at a company domain') and enumerates the exact types of changes returned. It also answers the intended user question, making it easy to distinguish from sibling tools like get_company_state or get_company_technologies.

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?

The description implies usage by framing the tool as answering 'what changed at this company and when?', but it does not explicitly say when to prefer this over siblings such as get_company_timeline or get_company_state, nor does it state exclusions or prerequisites.

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