Read or change sci-bot settings

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the dual-mode nature, the mutating effect ('applies the given keys'), and the return contract ('returns the settings afterwards'). However, it omits failure semantics — the SETTINGS_KEY_UNKNOWN behavior lives only in the schema — along with persistence and partial-application behavior, which are meaningful gaps for a mutating tool with zero annotation coverage.

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?

The entire description is one dense sentence that front-loads the read mode, then the write mode, then the return value — no filler and nothing redundant with the title. Every clause earns its place.

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 tool with one optional nested parameter and no output schema, the description covers both call modes and the return contract, while the schema documents the patch keys, value constraints, and the SETTINGS_KEY_UNKNOWN error. The remaining gaps — persistence across sessions and error cases beyond unrecognized keys — are minor for a simple settings tool.

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%: the patch object, citeFormat, minReferences, and answerLanguage all carry descriptions enumerating valid values, ranges, and the unrecognized-key error. The description adds only the read-versus-write framing of patch, which aligns with but does not exceed the schema's own 'omit to read them' note. The baseline of 3 applies because the schema does the heavy lifting.

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 states a concrete read behavior ('without a patch it reads the account settings') and a concrete write behavior ('with a patch it applies the given keys'), tied explicitly to the presence or absence of the patch parameter. The resource — account settings — is distinct from every sibling, which all deal with questions, conversations, or tokens. An agent can act on this immediately without guessing.

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 description gives clear conditional guidance: omit patch to read, include patch to change, and expect the updated settings as the result. It establishes natural when-to-use logic for both modes, though no alternative is named and no explicit exclusion is stated. Since none of the siblings is a plausible settings alternative, this omission is minor.

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