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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the description doesn't need to restate that this is a non-idempotent write. It adds real value beyond the structured data by warning that the call may silently create a duplicate of an existing contact. It stops short of saying what the response contains or how to undo a bad create.

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?

Three short sentences, front-loaded with the write marker and followed immediately by the constraint and the duplicate risk. Every clause carries distinct information, and the endpoint is tucked away at the end where it costs nothing.

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 17-parameter, zero-required create tool with no output schema, the description supplies the two things the schema cannot: the hidden required-field constraint and the duplicate risk with a mitigation path. The only gap is the absence of any return-value or failure-mode information, which would help an agent that must confirm creation succeeded.

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?

With 100% schema description coverage the baseline is 3, but the description adds a cross-field constraint the schema does not encode: the schema marks zero required parameters, yet the description reveals that email or mobile_number is effectively mandatory. It doesn't cover the many other fields, which the schema already documents.

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 opens with a specific verb and resource ("WRITE: create a contact") and names the API endpoint, so the agent knows exactly what it does. Differentiation from the create_* siblings is only implicit via the resource noun in the name, with no explicit contrast drawn.

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 states a hard prerequisite ("Freshsales requires an email or a mobile number") and explicitly routes the agent to an alternative first step: "search first (freshsales_lookup by email)". Both the when-to-use condition and the named alternative tool are given, leaving nothing to inference.

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