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

Annotations already cover readOnly, idempotent and non-destructive, so the description's job is to add context — it does: a hard 1000-record cap, inclusion of refused downloads, ordering by recency, and the API-key requirement. Missing is whether results can exceed 1000 or how to page past the cap.

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, front-loaded with the resource and its hard limit, then the use case, then the auth requirement. No 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?

For a simple read-only audit tool with full annotation coverage and a fully documented schema, the description covers scope, cap, and auth. Only pagination/behavior past the 1000-record limit is left 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 coverage is 100%, including a detailed api_key description covering header alternatives, so the schema does the heavy lifting. The description adds marginal meaning by implying the grant must be 'owned' and that the API key is required, but adds no format or scoping detail for grant_id.

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 gives a specific verb and resource ('Read the latest 1000 access attempts'), and the scope ('for an owned grant, including refused downloads') tells the agent exactly what data comes back. It doesn't explicitly contrast itself with similar-sounding siblings like get_share_status or list_shares, so an agent must infer the boundary.

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?

'Use this to see whether a share was opened' gives a concrete use case and implies the prerequisite that the grant must be owned. It doesn't state when to pick get_share_status instead, so alternatives are left to inference.

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