provider_change_password

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

Annotations already declare readOnlyHint=false, destructiveHint=false and non-idempotence, so the safety profile is covered. The description adds the meaningful 'local user' scoping hint but omits post-change behavior an agent would care about — whether existing sessions/tokens are invalidated, whether admin rights are required, and whether the caller can target other users.

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 lines, front-loaded with the action, no padding. Minor redundancy: the two opening sentences restate each other, and the raw POST path duplicates the annotation title, but nothing is confusing.

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 credential-mutating tool with no output schema, the definition covers what it does and the password policy is carried by the schema, but it leaves out authorization scope and side effects (session invalidation, whether an admin or only the self may invoke it). Adequate but with clear gaps for a security-sensitive mutation.

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%, and the nested body schema already spells out password complexity rules and the meaning of currentPassword/newPassword explicitly. The description adds nothing beyond that and leaves userUrn's semantics (whose password is actually changed) ambiguous, so the baseline of 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: change an existing local user's password, with the underlying endpoint given. It does not distinguish itself from the adjacent provider_update_user tool, so an agent cannot tell from the description alone which one to use for password changes versus profile edits, and the phrase "user's own password" slightly conflicts with the userUrn parameter that suggests any user.

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 word "local" implies a scope restriction (versus LDAP/SSO-backed users), which is the only usage guidance present. There is no statement of when to prefer this over provider_update_user, no mention of whether an admin may change another user's password, and no prerequisites such as needing the current password.

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