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

Annotations already establish readOnlyHint=true, so the safety profile is covered; the description adds behavioral value on top by disclosing the bounded retention behavior ('last ~50 checks') and the exact result contents (outcome/credits/reason). It does not mention ordering or pagination for older checks, but for an idempotent read-only history view this is a meaningful, non-redundant addition.

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?

A single em-dashed sentence that front-loads the user-facing purpose before giving the operational details (count cap and returned fields). Every word carries meaning; there is no filler or repetition of schema/annotation content.

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 list tool with a rich input schema handling the boilerplate parameteres, the description covers the essential invocation context: what it lists, the recency bound, and the result fields. With no output schema present, the description reasonably carries the return-format burden; only minor gaps remain — the exact meaning of `id` and whether checks are sorted newest-first — neither of which would block correct invocation.

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 75% — context, llm_model, and conversation_id are fully documented in the schema, so no duplication is needed. The one gap is the required `id` parameter, which has no schema description and is not explicitly clarified in the tool description; the title implies it is the monitor id, but the description itself never states that, so the agent must infer param semantics from the title.

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: lists a monitor's recent check history, with a bounded scope (last ~50 checks) and the fields returned (outcome/credits/reason). The diagnostic framing as the 'why didn't I get a webhook' view clearly distinguishes it from siblings like monitors_events_list and webhookEndpoints_deliveries_list, so an agent can select it without opening the 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?

The 'self-serve why didn't I get a webhook view' gives a clear, concrete trigger condition — a user asking why a webhook was not delivered. It implies the diagnostic context for use but does not explicitly name alternative tools or state when not to use it, which keeps it at a 4 rather than a 5.

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