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

Annotations only supply destructiveHint=true; the description adds genuine behavioral value by clarifying that the PUT-style call is semantically a partial update ('Only the fields you pass are sent'), which an agent could easily get wrong for a PUT endpoint. It still omits side effects such as invoice recreation when membership level changes, which the schema documents but the description does not surface.

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 front-load the action and the key partial-update caveat, with the API endpoint appended as a trailing reference. Nothing is wasted, though the endpoint citation is the least load-bearing element and could be dropped without loss.

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?

With 10 parameters at full schema coverage, one required argument, and no output schema, the description covers the essentials an agent needs: what can be changed, that updates are incremental, and that the target must exist. Mitigating details such as the invoice-recreation default and the uniqueness constraint on email live only in structured fields, leaving a small gap for a destructive-flagged mutation tool.

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 every parameter including nested field_values is already documented, and the description adds only a high-level grouping (names, email, membership level/status, custom fields). That grouping is a useful orientation but adds no syntax or constraint detail beyond the schema, so the baseline 3 applies.

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 and resource ('Update an existing contact') and enumerates the updatable surface (names, email, membership level/status, custom field values), which lets an agent separate it from create_contact and get_contact by verb alone. It stops short of explicitly naming a sibling or stating the precondition that the contact must already exist.

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?

'Update an existing contact' and 'Only the fields you pass are sent' imply when the tool applies and that it is a partial update, so an agent can infer the use case. There is no explicit when-to-use guidance, no statement of prerequisites beyond the name, and no routing away from alternatives such as create_contact for new records.

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