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

Annotations already declare readOnly/idempotent/non-destructive, so the safety burden is largely covered; the description nonetheless adds substantive context beyond them by stating the API key is never exposed and by naming the local-file policy. It does not mention cost, latency, or whether the server probe can fail, which keeps it below a 5.

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 primary purpose and then the field inventory, closing with the security guarantee. The list is dense but every item is meaningful content the agent would otherwise have to discover by calling; nothing is redundant with the annotations.

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 return shape needn't be spelled out here, and the description correctly focuses on scope and the confidentiality caveat. For a zero-parameter diagnostic tool with full annotation coverage, this is essentially complete, lacking only explicit guidance on when an agent should prefer calling it.

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, which is the baseline-4 case; there is nothing for the description to disambiguate and no schema gap to compensate for. The schema is fully empty and consistent with the description's framing as a no-input inspection call.

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?

A specific verb ("Show") plus an enumerated inventory of what the response includes: server version, endpoint host, model, request format, limits, local-file policy, and binary availability. An agent knows exactly what this tool reports, and it is unmistakably distinct from the only sibling, understand_video.

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 implied rather than stated: mentioning ffmpeg/yt-dlp availability hints this is a pre-flight diagnostic before video work, and the empty schema signals a safe zero-arg call. However, the description never says "call this first when..." or names any condition or alternative, leaving the agent to infer the trigger.

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

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

Annotations already declare readOnly, openWorld, non-destructive, non-idempotent; the description goes further by disclosing that page URLs are resolved with yt-dlp, that headers are sent only to the target host's host, that fps is applied only when the endpoint's request format supports it, and that failures surface as coded [CODE] prefixes plus _meta. That is substantive behavioral context an agent could not derive from the annotations alone.

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?

Content is front-loaded with purpose first, then input forms, then return fields, then constraints. It is a single dense block with some run-on clauses (the source-sentence and the error-sentence pack several ideas each), so skimming costs a little, but almost no sentence is 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?

For a six-parameter, open-world media tool with nested headers, the description covers input forms, duration limits, sampling hints, return fields, and an error-code taxonomy. An output schema exists, so the enumerated return values are a bonus rather than a necessity, and nothing an agent needs to invoke it correctly appears to be missing.

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 baseline is 3; the description still adds operational nuance beyond the schema by explaining the scraper-header use case for `headers`, the allowed-directory constraint on local paths, and the conditional application of `fps`. It stops short of adding format/syntax detail for the second-range parameters, which the schema already covers.

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?

Opens with a concrete verb+resource: "Watch a video and answer a question about it," and immediately scopes it to a video-capable model behind an OpenAI-compatible endpoint. The accepted `source` forms (page URL, direct media URL, local path) are named, so an agent knows exactly what class of input this tool consumes.

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 real conditional guidance: long videos require start_seconds/end_seconds, a short range yields more detail for fast motion like workouts, and question may be omitted for a general description. No explicit when-not-to-use or alternative tool routing, but the only sibling is get_server_info, which is not a plausible substitute for this task.

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