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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes further by naming exactly which actions are destructive (api-key-delete, oauth-revoke, oauth-revoke-all) and which are refused. It also signals the auth/consent flow implicitly through the action vocabulary, giving the agent concrete per-action risk information that the boolean annotations cannot.

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?

Two dense sentences that front-load the purpose before the enumeration, and every element earns its place (action groups, refusals, destructive list, read routing). Slightly list-heavy, but not padded.

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 25-parameter, action-dispatch tool with no output schema, the description is appropriately complete: it scopes the tool, names the alternatives, flags the destructive subset, and points to action='describe' for the per-action reference the schema declines to inline. Nothing critical is missing given the schema's own richness.

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 descriptions are unusually rich (per-action meaning of `code`/`token`, `scopes` syntax, `admin`/`account_settings` ceiling semantics, `agent_name` provenance caveat), so the schema carries the parameter burden. The description lists the action set but adds no parameter syntax or format detail beyond what the schema already provides, so the baseline 3 is correct.

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?

The description opens with a precise verb+resource ('Fastio sign-in and credentials (write)') and then enumerates the concrete operations covered — PKCE sign-in, signup, signout, API key CRUD, 2FA, OAuth session update/revoke. It explicitly carves out what is NOT handled here ('Password signin and 2fa-verify are refused') and routes reads to the sibling `auth` tool, so an agent can distinguish it from `auth` without opening either 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 both when to use this tool (write-side auth operations) and when not to ('Reads are on `auth`'), plus the explicit refusal cases ('Password signin and 2fa-verify are refused'). The alternative tool is named rather than implied, which is the textbook 5 condition.

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