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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely non-obvious context: the shape of returned fields, that matchReasons explain matches, and critically that 'Lower score is a closer match' — an inverted-scoring convention that would otherwise trip an agent. It stops short of mentioning result limits or pagination.

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 core verb+resource and the tool-routing sentence is placed last where it belongs. Slightly dense with parentheticals ('60-second transcript windows', field enumeration), but nearly every clause 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?

There is no output schema, and the description compensates by enumerating return fields (titles, summaries, transcript snippets, labels, relevance scores) plus the conditional timestampSec/matchReasons behavior. Combined with the routing guidance, an agent has everything needed to call and interpret this tool.

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 both enums (scope, mediaType) are fully documented in the schema, so the schema does the heavy lifting. The description adds only incidental context about transcript windowing and does not extend the meaning of any parameter. Baseline 3 is appropriate.

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 (semantic search) and resource (analyzed media library), and narrows scope to spoken transcript windows plus visual frames/clips. It also explicitly names the sibling it is not (echosaw_ask_media), so an agent can distinguish it from the other search-adjacent tool without opening a 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?

Gives direct usage guidance ('Use this to find previously analyzed media by topic, content, keyword, or a phrase someone said') and names the alternative with the exact condition that selects it ('To get a synthesized answer instead of a result list, use echosaw_ask_media'). Nothing is left to inference.

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