account_reauth

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

Annotations already supply the safety profile (readOnly, idempotent, non-destructive, open-world), so the description's added value is genuinely non-obvious behavioral context: this launches Google consent in a browser, meaning an interactive, user-present flow that cannot be silently automated. It also states the effect (refreshing tokens / granting scopes). It does not say whether old credentials are replaced or what happens if consent is abandoned, and there is mild tension with readOnlyHint=true given scope grants change account state.

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, each earning its place: purpose/conditions first, the key operational trait (browser consent) second, the call directive last. Zero filler.

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 purpose, triggers, mechanism and the parameter to pass, which is sufficient for a single-param auth tool with no output schema. Minor gaps: no statement of post-success guarantees (token verified? account state after scope grant) or failure behavior.

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 schema already explains that 'account' is the same as 'alias', so the baseline is 3. 'Pass the account alias' adds a small routing hint on which parameter to use, but the description never addresses the duplicate alias/account pair or why neither is required.

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?

Specific verb + resource ('Re-authenticate an existing Google account') with the two motivating conditions spelled out (dead refresh token, scopes after a profile change). 'Existing' implicitly separates it from the sibling account_add, so an agent can route between them 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?

Gives clear triggering conditions: the refresh token is dead, or scopes must be granted after a profile change. It does not explicitly say when to prefer account_add/account_write_config, but 'existing account' makes the boundary inferable. No exclusions or prerequisites (e.g. browser availability) are stated.

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