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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-derivable behavior: the required auth scope, the rule that the returned cursor must be passed back for the next page, and the prompt-injection warning that free text arrives in untrusted_fields to be shown but never obeyed. That last point is exactly the kind of behavioral context annotations cannot convey.

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 plus the security note, each load-bearing: purpose, permission, pagination, untrusted-content handling. Purpose is front-loaded and nothing is repeated or 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 two-parameter read-only list with no output schema, the description covers the essentials an agent needs to call it safely and paginate correctly. It stops short of describing the shape of a returned booking or the default page size, which would help since no output schema exists.

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 0%, so the description must carry the load. It explains cursor semantics well ('pass the answer's cursor back as cursor for the next page'), but says nothing about limit — no default, no hint that 1-100 is the page-size range, leaving only the schema's min/max to speak for it. Partial compensation warrants a middle score.

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 and resource with scope: 'List my bookings waiting for a review.' The 'waiting for a review' qualifier inherently separates it from list_booking_reviews (reviews already written) and review_booking (write a review), but no sibling is named, so the agent must infer the boundary from the scope wording alone.

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 supplies a prerequisite ('Needs `bookings:read`') and the pagination contract, which imply usage, but it never states when to pick this versus list_booking_reviews or when not to use it. No alternative routing is provided, so selection depends on inferring intent from the phrase 'waiting for a review.'

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