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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Pure analysis. Writes nothing.' largely reinforces structured data, but the enumerated list of rule categories adds genuine behavioral context about the depth of the check. It does not describe what the result looks like (pass/fail per platform, warning severity), which is the main behavioral gap given there is no output schema.

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, front-loaded with the action and followed by the scope list, with the safety disclaimer last. The enumeration is long but each item names a distinct rule dimension that a caller could not infer otherwise, so it earns its space.

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 7-parameter, no-output-schema validation tool, the description covers what is checked but says nothing about the shape of the response: whether results are per-platform, whether warnings and errors are distinguished, or whether anything is returned at all on success. With nested platformMeta left structurally undocumented, an agent must open the schema and still guess at the return contract.

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 coverage is 100%, so the schema already documents every parameter, including the YouTube-only title and the photo-vs-video caption limit distinction. The description gestures at the same concepts (titles, media requirements) without adding syntax, format, or priority details, so 3 is the appropriate baseline. The nested platformMeta object remains explained only as 'platform-specific publishing options' in both places.

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 verb and resource ('Check a caption against each target platform's posting rules') and then enumerates exactly what is validated: caption length, media requirements, hashtag ceilings, link clickability, YouTube titles, and PII/prohibited content. Combined with 'before scheduling', an agent can immediately tell this apart from write-side siblings such as sprkly_schedule_post or sprkly_draft_post.

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 phrase 'before scheduling' gives a clear trigger point in the workflow, positioning this as a pre-flight check rather than a publishing action. It stops short of naming the sibling to call afterwards or stating what to do when validation passes or fails, so there is no explicit when-not guidance.

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