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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered by structured data. The description adds real behavioral context beyond that: a minimum query length of 3 characters and a hard result ceiling of 'up to 25'. It does not state whether results are silently truncated, in what order they come back, or whether matching is case-insensitive.

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 short sentences, front-loaded with the matching semantics and the result cap, with no filler. The only friction is that 'Returns up to 25' and the schema's 'Default 10' create mild ambiguity about whether 25 is a default or a maximum.

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 two-parameter read-only search whose annotations and schema are already rich, this is close to sufficient, but ordering of results and match semantics beyond 'contains' (case sensitivity, which fields beyond email and name) remain unstated. Nothing an agent needs in order to not fail is missing, but a correct call could still surprise on result ordering.

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 coverage is 100%, which sets the baseline at 3, but the description genuinely adds a constraint the schema omits: the 3-character minimum for the query field (the schema has no minLength). The phrase 'Returns up to 25' also clarifies the effective ceiling, though it sits slightly awkwardly beside the schema's documented default limit of 10.

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?

A specific verb-plus-resource ('Finds contacts') combined with the matching rule ('whose email address or name contains the search text') tells an agent exactly what this returns. It does not contrast itself with get_contact or get_contact_activity, so the agent must infer the search-versus-lookup split from the names alone.

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 only implied: the phrase 'contains the search text' hints that this is for partial-text discovery rather than fetching a known contact by ID, which routes toward get_contact implicitly. No explicit when-to-use, when-not-to-use, or named alternative is given.

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