update_access_policy

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

Goes well past the annotations: it discloses that subjects/targets are wholly replaced (not merged), that omitted name/description/effect/enabled retain stored values, that conflicts return 409 and are not retried, and that the caller should reread before retrying. This is exactly the conflict/auth-and-omission context annotations cannot carry.

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 dense sentences, front-loaded with the destructive replace scope, then preconditions, then conflict behavior. Nothing is padding and the ordering matches how an agent should decide and then call.

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?

An output schema exists so return values need not be explained, and the description still covers the mutation scope, version prerequisite, conflict handling, and field-omission rules for an 8-parameter destructive tool. Nothing needed to invoke it correctly is missing.

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 100% so the baseline is 3, but the description consolidates omission behavior across four parameters (name, description, effect, enabled) and pins the source of 'version' to get_access_policy — omission semantics for name/description are not stated in the schema. It adds real meaning rather than echoing field names.

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 ('Replace an access policy's complete subjects and targets') and makes the replacement semantics explicit, which separates it from create_access_policy/delete_access_policy and from partial-update siblings. An agent knows exactly what the call mutates without opening the 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?

Gives a hard precondition ('Requires the current version from get_access_policy') and spells out the failure mode and remedy ('a stale version returns HTTP 409 without retrying... reread before retrying a conflict'). It stops short of naming when-not-to-use versus create_access_policy, so it is clear context without explicit exclusions.

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