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

With no annotations provided, the description does useful work: it declares 'Read-only', caps the result at ~20 people, and warns that refresh=true is slower. It does not say what happens if the research hasn't finished, whether refresh costs credits, or whether a rebuild invalidates the cached audience — meaningful gaps for a tool whose only mutating path is that 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?

Two tight sentences, front-loaded with the read-only safety signal, then the payload, then the refresh trade-off. Every clause carries information; nothing is padded.

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?

There is no output schema, and the description compensates by enumerating the returned fields, which is exactly what an agent needs to decide to call it. The missing pieces are the prerequisite/error condition for an unfinished research and clearer job_id semantics, but overall it is sufficient to invoke correctly.

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%, so the description must carry both parameters. It handles 'refresh' well (true = rebuild, slower) but leaves 'job_id' implicit — an agent must infer from 'of a finished research' that it identifies the research job, and nothing says the format must be a UUID.

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 (get) and resource (the instant audience of a finished research) plus the concrete payload: up to ~20 people with company, position, country, LinkedIn, email and fit rationale. That clearly separates it from other audience getters like get_custom_audience or get_audience, though it never names a sibling outright.

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 phrase 'of a finished research' and the reference to the wizard's 'buyers already found' cards give a clear context for when to call it, and 'refresh=true rebuilds it (slower)' tells the agent how to opt into recomputation. It stops short of naming alternatives (e.g. sdr_get_research, sdr_materialize_research) or stating exclusions.

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