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

Annotations cover readOnly/idempotent, and the description adds real non-annotation behavior: nothing is changed, it mirrors the planner's own check, customer keywords and published articles are never included, and the `degraded: true` partial-result condition with an explicit retry instruction.

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?

Front-loads the core purpose, then layers scope exclusions, mutation safety, and the degraded caveat in a logical order. Slightly dense with a nested parenthetical, but every clause carries information.

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 carries the burden of explaining the return signal (`degraded`), and it does so. It does not describe the shape of a returned match entry, but the safety, scope, and error semantics an agent needs to call and interpret it 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?

Only one parameter (`site`) and schema coverage is 100%, with the allowed value enumerated in the schema. The description adds no parameter-level detail, which is acceptable here but earns the baseline rather than extra credit.

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 with scope qualifiers: 'scheduled, not yet written articles Blawgy proposed' filtered by the site's 'Never write about' list. It explicitly excludes keywords and written/published articles, so an agent can distinguish this from list_articles or get_plan without opening schemas.

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?

Gives clear operational context: same check the planner uses, retry when `degraded: true`, and the concrete next step of calling remove_plan_entry with the id to drop a match. It stops short of naming an explicit alternative to read planned entries in general, so not a full 5.

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