video_recipes

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

Annotations only cover safety/idempotency flags, and the description goes well beyond them: it discloses that content is operator-written rather than generated per call, that computation is local/server-side with no personal data processed, that billing is a lookup charge, and that recipes are advisory (consent, location and rights clearance). It also lists response fields including 'truncated', which matters for a capped result set. Minor deduction for the slightly self-contradicting 'no payment' vs 'the payment buys the lookup' phrasing.

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 sentence is front-loaded and strong, but the tail is dense boilerplate: LOCAL development notes, payment justification, and a data-processing disclaimer that reads as platform-wide legal text rather than tool-specific help. Several sentences do not earn their place in a selection decision.

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 enumerates the returned fields (dataset, total_matches, truncated, recipes, index, categories, coverage) and flags truncation and the id index needed for follow-up calls. That covers what an agent needs to call and chain it, though it omits any guidance on result size limits or pagination behavior in practice.

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% and every parameter is already described in the schema, including the id pattern example. The description adds only light framing ('plain words matched against title, description and ideas' is in the schema itself, and the note that the response lists all recipe ids is the one genuinely new hint). Baseline 3 applies.

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 concrete verb and resource plus its full payload: 'Get ready-made video recipes with hook, shot list, interview questions, equipment, recording time, platforms and follow-up formats'. The 'one shoot, several posts' framing and the filter modes make it unmistakably distinct from siblings like video_project_plan or shoot_day_plan.

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 explains how to narrow results ('Filter by category, words or exact recipe id') and which language switch to use, which implies when to reach for it. But it never contrasts with the adjacent planning tools (video_project_plan, shoot_day_plan, content_month_plan) despite 37 siblings, and there is no explicit when-not guidance beyond a legal/consent caveat.

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