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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is the disclosure that results include revoked grants — not just active ones — which is a non-obvious filtering trait. It also gives a pagination rule ('Continue while has_more is true') that tells the agent how to terminate the loop rather than relying on the output schema alone.

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 scope and caller role, then pagination. No filler. Minor deduction for the cryptic fragment 'Person only.', which is terse at the cost of clarity.

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?

Output schema exists, so the description correctly does not explain return fields, and the two-parameter surface is simple. Auth/role requirement and pagination are both covered; the only real gap is the ambiguous 'Person only' constraint and the undocumented limit parameter.

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?

At 50% schema coverage, only cursor is documented ('The next_cursor from the previous page'); limit is undocumented in both schema and description despite a meaningful 1-50 bound. The description's pagination sentence indirectly implies cursor usage but says nothing about page-size control or ordering.

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 ('list ... spending grants') with explicit scope: active AND revoked grants the caller gave to linked agents, plus the monthly accepted commitments included in each record. An agent can distinguish this read operation from the sibling mutators agent_grant_set and agent_grant_revoke, though no sibling is named.

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 a prerequisite caller identity ('As the account owner') and a restriction ('Person only'), which is more than most list tools offer. However it never says when to prefer this over agent_list or agent_get-style lookups, and 'Person only' is left unexplained (human account? non-agent caller?).

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