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

Annotations declare only readOnlyHint=false and destructiveHint=false; the description adds the human-review gate ('a person at INITE reviews before it shows') and precise auth behavior ('a guest call answers 401 and starts the OAuth flow'). These are behavioral traits the annotations cannot convey and are exactly what an agent needs to set expectations on latency and failure.

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?

Front-loaded with the verb and purpose, and nearly every clause carries payload (field mappings, exclusions, auth). The field list makes it dense and slightly run-on, but there is no filler sentence.

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?

With no output schema and thin schema coverage, the description supplies the missing pieces: editable fields, review-gated result, auth behavior, and a faster alternative. An agent could invoke it correctly, though the return/confirmation shape after submission remains unstated.

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 only 20%, so the description must carry the load, and it does: it maps each enum value to its companion parameter ('name' with name, 'pricing' with a nested {model, freeTier, startsAt{amount,currency,per}|null,source} object, 'note' with free text). It does not document the required 'domain' beyond the schema's own description, keeping it just short of a 5.

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 (propose a correction) and resource (your card), then enumerates the exact editable fields (name, pricing, note) and explicitly excludes the one-line description and verdicts. An agent can distinguish it from sibling tools like atlas_owner_set_read_pages without opening any 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?

Names an alternative route (set_read_pages is the faster way to a price) and states exclusion conditions (description/verdicts not editable), plus an auth prerequisite. What's missing is explicit framing of when a proposal is preferable to just setting read pages, but the routing signal is present.

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