video_guard

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

With no output schema and annotations that only say readOnly=false, idempotent=false, destructive=false, the description carries real weight: it discloses scope (only reviews owned by this connection, host-chosen scope), explicit non-effects (does not start jobs, does not interpret images, does not affect unrelated chats), concrete limits (eight continuations, stop after three unchanged checks), and an auth/trust prerequisite. That is exactly the behavioral context the annotations lack.

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?

Four sentences, each carrying distinct information: identity, scope, non-effects, limits, prerequisite. It is front-loaded with what the tool is and what it returns. Slight density/jargon cost keeps it from a 5, but there is no 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?

Because there is no output schema, the description should say what comes back; 'returns a hook decision' plus the retry/continuation limits covers the important behavior, but the actual shape of the decision is never described. Given zero parameters and a self-contained adapter role, this is nearly complete but leaves the return contract implicit.

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, so the baseline is 4. The description appropriately spends no words on argument semantics and instead explains the implicit scope selection ('host-chosen scope rather than forcing all pictures or ASR'), which is the only meaningful input-like concept here.

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 states a concrete verb and resource: it returns a hook decision covering unfinished reviews owned by THIS MCP connection. It also distinguishes itself from siblings by declaring it does not start jobs or interpret images, which separates it from video_start/video_read/video_review. The phrase 'Codex Stop-hook adapter' is jargon that an agent without Codex knowledge may not resolve.

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: 'Optional' plus 'Requires host hook configuration/trust; standalone MCP remains usable without it' tells the agent the precondition and that it can be skipped. However, no sibling is named as an alternative and no explicit 'call this when X' condition is given, so the agent must infer that only a configured host hook should invoke it.

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