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

Annotations only give generic hints (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description goes well past them: it discloses the tokenless data source, that rows land in the Meta → Comments feed, that auto-moderation rules fire on new rows, and that resulting hide/delete/reply actions are queued for the extension via claim_meta_commands. That is genuine side-effect disclosure for a non-readOnly write. It does not explain what happens on duplicate comment reports, which matters given idempotentHint=false.

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?

The core purpose is front-loaded, but the rest is a single dense run-on paragraph that packs the data source, storage destination, moderation pipeline and a parameter note into one breath. The information is largely useful, yet the lack of segmentation makes the key call-time facts harder to extract than they need to be.

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 tool with a nested object schema, four parameters and no output schema, the description covers the pipeline end to end — source, storage, side effects and command queueing — which is what an agent needs to invoke it sensibly. Gaps are the batch size limit, duplicate-handling behavior and what the response contains.

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 only 50%, so the description has to carry weight — and it does, explaining that `pages` is the FB user's own pages used for own-author exclusion so the brand's own comments are never moderated, which clarifies intent beyond the schema's terse note. It also adds a scope constraint (last 7 days, dark posts and IG media) not encoded in the schema, though it says nothing about the 1000-item cap or how the comments array items are populated.

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 specific verb and resource — reporting comments on posts behind an ad account's ACTIVE ads, limited to the last 7 days and to FB dark-post plus IG media comments — so the scope is concrete. It names register_meta_cabinet and claim_meta_commands as related tools, but never contrasts itself with list_meta_comments, the sibling an agent would most plausibly confuse it with.

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?

It implies usage context through 'what the Torvex browser extension reads from a logged-in Ads Manager session on its comments timer', which tells the agent this is an ingestion endpoint driven by the extension rather than an ad-hoc query. There is no explicit when-to-use / when-not-to-use statement and no instruction about call frequency or preconditions beyond the implicit timer.

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