monitors_update

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

With zero annotations, the description carries the full behavioral burden, and it delivers: it discloses that the call is free, and—critically—that changing `target_type` or `sitemap` resets the stored diff baseline (fingerprint, snapshot, or URL set), causing the next check to establish a fresh baseline. This is exactly the kind of hidden side effect an agent needs to anticipate, and it is stated with specific field names and consequences.

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 tight sentences, each earning its place: purpose, ownership/cost, and the critical side-effect caveat. The most important disambiguators are front-loaded, and there is no filler or repetition of schema 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 2-parameter update tool with a nested request object and no output schema, the description covers the non-obvious essentials: cost, ownership, partial-update semantics, and the baseline-reset side effect. It does not describe the success response or error cases, but those are not needed to invoke the tool correctly. The only notable omission is a fuller enumeration of what fields `request` accepts, though the examples given hint at it.

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%, so the baseline is 3. The description adds value beyond the schema by naming `target_type` and `sitemap` as concrete fields inside the nested `request` object and attaching semantic weight to them (they trigger baseline reset) — information the schema's generic 'Fields to update' lacks. It also clarifies the request object's partial-update semantics.

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 opens with a specific verb-plus-resource statement ('Update a website-change monitor') and immediately refines it with 'Partially updates one of the caller's own monitors,' clarifying both the partial (PATCH-style) semantics and the ownership scope. Among the monitors_* siblings (create, delete, get, list, checks), 'update' is unambiguous and distinguishable without inspecting any other 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 ownership scope ('one of the caller's own monitors') and the partial-update framing give clear context for when this tool is appropriate: modifying an existing monitor the caller owns, rather than creating, deleting, or reading one. It does not explicitly name sibling alternatives or state exclusions (e.g., for replacing everything use create and delete first), so it stops short of full routing guidance.

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