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

Beyond the readOnlyHint/idempotent/destructive annotations, it discloses real behavior: which payload each part returns, that transcript and frames are paged with total and next_cursor, that the adapted script appears only for own analyses, and the trust caveat that nothing is marked verified. Minor gap: no mention of limit semantics or failure behavior for a stale/invalid ref.

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?

Front-loaded with the use case, then a compact per-part breakdown that avoids repetition; nearly every clause carries payload information. It is dense and slightly run-on (multiple semicolon-chained clauses), but nothing is wasted.

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?

There is no output schema, so the description must describe return shape, and it does per part, including pagination and the verification caveat. The remaining holes are the unstated meaning of limit=0 and cursor format, which an agent would need for large transcript or frame fetches.

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?

With schema description coverage at 0%, the description carries the burden and does so for the important params: all three 'part' values are enumerated with their contents, and both 'ref_type' enum values are explained (job = own analysis, library_reel = shared card). 'ref_id' is only implied ('by a ref') and 'limit' default 0 is never explained, which keeps this below a 5.

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 ('the full stored analysis of one video') and pins down exactly which identifiers it consumes ('by a ref from search_library', with both ref_type variants defined). It also explicitly separates itself from get_analysis for Threads posts, so an agent can route without opening the schema.

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?

Opens with an explicit when-to-use trigger ('Use this when you need the full stored analysis'), states the prerequisite ref source, and names a when-not plus the alternative tool ('Not for a Threads post analysis ... get_analysis reads it'). No inference required to choose between siblings.

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