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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is partly covered. The description adds real value beyond that: 'tags replaces the whole tag list' discloses destructive replace semantics that an agent must know before calling, and the consent scope boundary prevents an unintended side effect.

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 action and its fields, followed by the two highest-risk facts (tag replacement, consent exclusion). No filler and no repetition.

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 destructive mutation with no output schema and a nested attributes object, the description covers the important behavioral facts — replace semantics for tags and the consent boundary. It stops short of noting what happens to non-listed fields or how attribute name collisions resolve, but the schema partially covers the latter.

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 75%, so the baseline is 3; the schema already documents tags ('complete new tag list'), contactId, and attributes ('merged into the existing ones'). The description paraphrases name/tags/custom fields and restates the replace behavior already in the schema, adding little beyond it and nothing about the undocumented contactId format.

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 (changes) and resource (a contact) and enumerates the mutable fields: name, custom fields, tags. It is clear what the tool does, but it never names the obvious sibling tag_contacts or create_contact, so the agent must infer the boundary between this and the tag-management tool.

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?

The clause 'This action does not change marketing consent' implicitly routes consent changes to set_contact_consent, which is useful boundary-setting. However, there is no explicit when-to-use statement and no naming of the alternative tag_contacts tool, so usage is only implied rather than guided.

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