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). The description adds genuinely non-obvious behavior: monitors on a view-shared page have no id and must be addressed by page_id and slug, and it enumerates the returned fields (status, page, access). That is real value beyond the structured data.

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?

Two sentences, front-loaded with scope and then the id-less caveat. Every clause carries information and nothing is 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?

With no output schema, the description usefully names the returned fields and — critically — explains the edge case where shared monitors lack ids and how to address them. Only the return-format/pagination and filter behavior are 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% and each parameter is documented there, so the baseline is 3. The description only hints at page_id ('or on one page') and says nothing about tag or query semantics, adding no meaning beyond the schema.

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 the monitors') with an explicit scope choice: all pages the account can see, or a single page. It reads clearly against siblings like get_monitor and create_monitor, though it never names the list-vs-get distinction outright.

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 implies the two usage modes (all pages vs one page) but gives no explicit guidance on when to prefer this over get_monitor for a single monitor, nor on how tag/query filtering interacts with those modes. Usage is inferable but not stated.

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