search_saved

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and world scope are covered. The description adds genuine context beyond them: the corpus is limited to transcripts fetched before, and results are ranked best-first with video, timestamp, matching line and deep link. It says nothing about result caps or what happens when nothing matches, which matters for a search tool.

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?

Three short sentences, zero waste, with the scope constraint front-loaded and the return shape before the usage hint. Every sentence earns its place.

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 simple two-parameter read tool with no output schema, the description covers purpose, corpus scope, return shape and a usage trigger. The remaining hole is parameter behavior, especially the undocumented limit, which the empty schema descriptions leave unfilled.

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 0%, so the description carries the full burden for the two parameters and does not meet it. Neither the query semantics (keywords, phrases, natural language?) nor the limit parameter (default 10, maximum, effect on ranking) is addressed anywhere.

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?

"Search every transcript fetched before, across all saved videos" gives a specific verb and a precisely scoped corpus, which implicitly separates it from search_transcript (single transcript) and list_saved (no query). It stops short of naming those siblings, so an agent must infer the split rather than being told it.

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?

The final sentence gives a concrete trigger: use it when the user refers to something they watched or asked about earlier. That is real when-to-use guidance, but there is no explicit exclusion (e.g. what to use for a transcript never fetched before) and no named alternative.

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