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

With annotations declaring readOnlyHint=false and openWorldHint=true, the description adds real context the annotations cannot: 10 AI credits (first per org free), a quote-then-confirm gate, and the fact that direct media links expire within hours so they must be downloaded immediately. It does not contradict the annotations — 'reference and analysis only' refers to content republishing, not to the credit spend that justifies readOnlyHint=false. What keeps it from a 4-5 is that 'its numbers' is left undefined despite there being no output schema, so the agent cannot tell the user what metrics they will actually get.

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?

Purpose is correctly front-loaded, but the body is one undifferentiated block that mixes return values, download guidance, transcription workflow, legal caution, pricing, routing, and a long confirmation protocol. The confirm rule is restated at least three times ('SPENDS AI CREDITS ONLY WITH confirm: true', 'Call it first without confirm', 'call again with the same arguments and confirm: true'), which aids safety but costs density.

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 no output schema, the description usefully sketches the return shape (caption, duration, ordered media list with expiring links) and warns about link expiry, plus it covers cost, the approval gate, and the downstream transcription path via get_edit_playbook. The one real hole is that 'numbers' is never expanded into the actual metrics returned, which an agent needs to describe results to a user.

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, but the description meaningfully extends the `confirm` parameter beyond its schema text by explaining the full quote-approval loop and that one yes covers only the approved plan. It also clarifies that `url` can be an Instagram /p/ carousel or a TikTok/YouTube link, which the schema does not. workspaceId and idempotencyKey are left entirely to the schema.

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?

States a specific verb and resource — fetch one public reel/post/video by URL — and immediately enumerates the platforms and the returned fields (numbers, caption, duration, media links). It names the sibling tools it is NOT (research_account, research_niche, get_research), so an agent can route without comparing schemas.

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?

Explicitly hands off to research_account for account-level posts, research_niche for topics, and get_research for previously run analyses (noting it is free). It also specifies the mandatory two-phase call pattern: call without confirm to get a quote, relay it to the user, then repeat with identical arguments plus confirm: true.

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