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

Adds real semantics beyond the annotations: selective field updates, list replacement for group_ids, and empty-string clearing of email/details. Annotations already flag destructiveHint and idempotentHint, so the description doesn't need to restate risk, but it could note that replacement of group_ids is the destructive path rather than leaving the agent to infer it.

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 compact clauses with zero filler, front-loaded with the "WRITE:" marker that signals mutation first. Every clause carries distinct operational meaning.

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?

Covers the mutation model, clearing semantics and list-replacement hazard for an 8-parameter tool with a nested details object and no output schema. It leaves out error behavior (e.g. what happens with an unknown resource_id) and return shape, which the agent must assume.

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% and the schema itself already documents the group_ids REPLACES behavior and the empty-string clearing rule, so the description mostly restates structured data. It adds a little emphasis on partial-update semantics but no new per-parameter detail (e.g. color pattern, details key range).

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?

Leads with an explicit operation class ("WRITE: change fields of an existing resource") naming both verb and resource, and the word "existing" cleanly separates it from the sibling create_resource. The endpoint reference (POST /api/resources/{id}) reinforces the target so an agent can distinguish it from update_event and update_group without opening a schema.

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?

States the operative condition clearly: only the fields you pass are changed, so partial updates are safe. It does not name alternatives or exclusions (e.g. use create_resource for new resources, delete_event for removal), so routing still requires inference from the name.

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