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

Annotations (openWorldHint=true, idempotentHint=false, destructiveHint=false) already signal this is not a destructive operation, and the description adds valuable behavior beyond them: the default new-only filter and the webhook POST side effect. Disclosing that it can POST to an external endpoint is exactly the kind of non-obvious behavioral trait an agent needs before invoking.

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 with zero waste: sentence one names the tool and purpose, sentence two states the default filtering behavior and webhook capability. The most decision-relevant information (new posts only, webhook POST) is front-loaded.

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 10-parameter, stateful monitoring tool, the description covers the essential invocation semantics: what runs, the default behavior, and the side-effecting webhook delivery. The return structure beyond 'new public posts' is not detailed and there is no output schema, but the schema's resetState and onlyNew descriptions compensate by explaining the state model (saved Task, seen-set/cursor).

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 100%, and the parameter descriptions are detailed — handle patterns with or without @, excludeTerms removing posts 'before delivery and billing', resetState explaining the saved seen-set and cursor. The tool description itself adds no parameter-level meaning, but with complete schema coverage the baseline 3 applies.

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 action ('Run the Apify Bluesky monitor') and names the full watch scope: keyword, handle, mention, and hashtag alerts. It also states two concrete behaviors — returns only new posts by default and can POST to a webhook. With no sibling tools to differentiate from, this is clear and unambiguous, though the verb 'Run' is slightly generic without the resource name.

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 words 'scheduled' and 'monitor' imply recurring alert usage, and the schema's onlyNew/resetState parameters reinforce that this is a stateful monitoring tool rather than a one-off search. However, there is no explicit when-to-use or when-not-to-use guidance, and no alternatives exist to be ruled out, so usage context is left to inference.

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