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

With only destructiveHint=true in annotations, the description usefully adds PATCH/partial-update semantics ('only the fields you pass are sent') and the required-field quirk. It does not cover auth needs or rate limits, but it meaningfully exceeds the annotation baseline.

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?

Four tight sentences, front-loaded with the 'WRITE:' marker, each carrying distinct information (scope, partial-update, required-field caveat, endpoint). Nothing redundant.

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 22-param mutation with no output schema and minimal annotations, the description covers the crucial behaviors an agent needs: write nature, partial update, required fields, and exclusion of contact data. Return format is unnecessary since no output schema exists.

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 59% across 22 params, so the description must help. It explains the important first_name/last_name required-even-when-unchanged behavior and enumerates representative editable scalar fields, adding value beyond the schema for the parameters that matter most.

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 (change/update) and resource (scalar fields on an existing constituent) with concrete example fields. It clearly delimits scope by excluding addresses, emails and phones, though it does not name the sibling tool that handles those, so differentiation from siblings is partial.

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?

Gives real operational guidance: 'Only the fields you pass are sent' and to pass current values from lgl_get_constituent when first_name/last_name are unchanged. It signals which data is out of scope, but never names the alternative tool for editing contact details.

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