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

Beyond the readOnlyHint annotation, the description discloses that documents are untrusted visitor-controlled data, that ordering is most-recently-updated first, that pagination continues via an opaque cursor, and that writes belong to the app's own code. These are meaningful behavioral disclosures that help an agent use the tool safely.

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 sentences front-load the core operation, then pagination, then a critical security warning and read-only note. There is no filler, and the IMPORTANT warning earns its place because it changes how the agent must treat returned document 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 an 8-parameter paged query with no output schema, the description covers the essential operational facts: graduated-app scope, cursor continuation, termination, default ordering, and untrusted document content. The remaining parameter details are already present in the input schema, so nothing essential is missing for selecting and invoking the tool.

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?

The description adds important cursor semantics not fully captured in the schema: pass the returned cursor for the next page, and no cursor means the end. It also reinforces the default updatedAt ordering. The schema already documents sort, direction, limit, and where filters in detail, so the description appropriately supplements rather than repeats.

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 'Read one page of a collection from a GRADUATED app's queryable store,' giving a specific verb, resource, and scope. It makes the paging behavior and default ordering explicit, which distinguishes it from sibling tools like record summaries or data writes.

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?

It states exactly how to fetch a page, how to continue with the returned cursor, and how to detect the end. The read-only note also indicates this tool is not for writes, though it does not explicitly name sibling alternatives for summary or non-graduated data access.

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