Pages revised since you read them

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

Annotations already establish read-only, idempotent, non-destructive behavior, but the description adds non-obvious traits the annotations can't convey: the inbox is side-effect-free while fmrl_get mutates seen-state, removed/expired pages surface exactly once, and an empty result is the signal that nothing is new.

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, each carrying distinct information: what is returned, how to consume it (with the seen-state caveat), and edge-case behavior plus sibling routing. Front-loaded with the core purpose and zero filler.

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 an output schema present, the description needn't document return values, yet it still notes the newest-first order and revision-author field. For a zero-parameter, read-only listing tool, everything an agent needs to call and interpret it is covered.

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 tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate. It correctly implies no filtering input is needed, since scoping is derived from the caller's watch list and read history.

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 ("List the pages you watch") plus precise scope — someone else revised them since your last read — and the ordering and payload (newest first, with who made each new revision). It also distinguishes itself from fmrl_list by naming the published-pages sibling case.

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?

Explicitly routes the agent: read discovered pages with fmrl_get because that marks them seen, whereas the inbox marks nothing. It also names the alternative for a different case ("For the pages this key published, use fmrl_list"), so selection between siblings is unambiguous.

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