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

Annotations cover read-only/idempotent/open-world, but the description adds meaningfully more: it is FREE (no payment required), payer-scoped to the caller's own runs only, sorted newest-first, and it explicitly defines the empty-result semantics and the status enum values (active | paused | spend_cap_reached). These are behavioral traits the annotations do not 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?

Front-loaded with 'FREE' and the core purpose, and the dense first sentence efficiently packs scope plus return fields. Minor redundancy: 'No payment required' restates 'FREE', and 'Strictly personal' restates 'the payer you name', so a little trimming is possible without losing information.

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 only one required parameter and an output schema already present, the description is more than complete: it covers scope, ordering, cost, empty-state behavior, and returned fields. An agent has everything needed to invoke and interpret the result correctly.

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% (payer has only a hex pattern, no description), so the description must compensate. It does: 'every appointment registered for the payer you name' and 'reads only the named payer's own runs' establish that payer is the owner key scoping the listing. It adds semantic meaning, though it omits the address-format nuance (that lives in the pattern).

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 specific verb+resource (list the payer's scheduled runs, newest first) and enumerates the returned fields: question, subject, spend cap, credits spent, status, next run time, last decision. It also carves out its scope against siblings with 'no cross-payer listing exists', so an agent can distinguish it from other listing tools without opening a 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?

Usage context is explicit: it reads your own payer's runs, requires a named payer, and 'an empty list is data (nothing registered), not an error'. The exclusion ('Strictly personal... no cross-payer listing exists') clarifies when this is the wrong tool for cross-payer needs. It stops short of naming the create-side sibling (tollbridge_stand) as the alternative for registering runs.

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