search_parties

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add behavior beyond safety. It adds the key behavioral fact that results come in Capsule's default order and no sort parameter is supported, which is not visible in the schema or annotations. It doesn't overpromise details like result formatting, but the added ordering note is genuine behavioral disclosure.

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 compact sentences with no filler. The first sentence states the core action and resource; the second adds the caveat and the alternative. This is appropriately front-loaded and every clause earns its place.

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?

For a simple read-only search/list tool, the combination of the description and the input schema covers what the tool does, when to use the sibling filter_parties, the supported ordering behavior, and pagination parameters. There is no output schema, so an agent does not get a result shape, but the description's 'returns results' plus the tool's plain object domain is sufficient for selection and invocation. Minor gaps like exact result fields exist but are not critical here.

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?

The schema already documents q, embed, and since with meaningful descriptions, so the description only clarifies that q can be omitted to list all parties ('search or list') and that sorting is not an available parameter. With moderate schema coverage (60%), the description contributes a little but leaves page/perPage and the interaction between q and since to the schema. This is adequate but does not reach significant added param semantics.

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 uses a specific verb ('search or list'), names the resource ('people and organisations in Capsule CRM'), and immediately clarifies its scope. It also distinguishes itself from filter_parties by saying structured queries belong there, so no sibling ambiguity remains.

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?

It explicitly tells the agent when not to use this tool: structured queries like 'most recent', 'tagged X', or 'added this month' should go to filter_parties instead. It also states the sorting limitation, which helps an agent decide whether this tool can satisfy a request. This is explicit routing guidance rather than implied context.

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