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

The description discloses the key behavioral trait: calling this tool advances the cursor, meaning results are consumed and a repeat call will not return the same pages. This adds real value beyond the readOnlyHint=false annotation, which only signals mutation without specifying what state changes occur.

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, zero filler. The core behavior and side effect are front-loaded, and the no-id variant is appended as a useful operational note. Every clause earns its place.

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 tool with no output schema, the description covers the action, the side effect, and the primary call variant. The notable gap is the undocumented limit parameter, and the return value is only vaguely implied as 'pages.' Still, the essentials for a correct call are present.

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 50% — the id parameter is already documented in the schema ('omit to check all'), and the description mostly echoes that. The limit parameter has no schema description and no mention in the tool description, so its semantics (limiting how many pages are returned) are left entirely to inference. The description partially compensates but does not fully cover the gap.

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 and resource ('Return pages matching a watched query') with a precise scope ('indexed since the last check'). The cursor-advance side effect cleanly separates it from siblings like watch_query (creation) and list_watches (listing). This goes well beyond the vague title 'What is new for a tracked query.'

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 gives clear context on when to use the tool ('indexed since the last check' implies a polling/checking cadence) and provides explicit parameter-level guidance ('Call with no id to check all of your watches at once'). It does not name alternative tools or state when not to use it, but the context is strong enough for an agent to decide appropriately.

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