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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the verdict is derived purely from technical metadata rather than the file itself, and the return value is a per-platform verdict with each check's message, which tells the agent the output is a structured audit rather than a boolean.

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 purpose and the platform dimension, with the parameter inventory and return shape following. The dense enumeration is efficient rather than padded; no sentence is redundant.

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?

No output schema exists, and the description does give a rough return shape ('verdict per platform with each check's message'), which is the right thing to include. But for a 13-parameter tool it leaves open which platforms are evaluated, how partial metadata affects verdicts, and whether a pass/fail plus message is the only payload — gaps an agent would want closed.

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?

With 69% schema coverage the schema already documents most parameters, including rotation-aware width/height and codec formats. The description enumerates the same facts in prose (size, length, dimensions, frame rate, codecs, sample rate, container, HDR, fast start), which confirms the model but adds little syntax or format meaning. It also never clarifies that only fileSizeBytes is required and that omitted optional facts likely weaken or skip certain checks.

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 ("Says whether a video will post on each platform") and immediately scopes what 'posting' means (Reel, Short, video, IG/FB Story). That level of specificity separates it cleanly from siblings like check_caption or get_image_sizes without the agent needing to open a schema.

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?

Usage is only implied: an agent can infer this is a pre-publish validation step, and the phrase 'from its technical facts' hints that no file upload is involved. However, there is no explicit when-to-use versus when-not guidance, no mention of the alternatives (get_platform_specs, check_caption), and no stated prerequisites or exclusions.

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