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

Annotations already cover read-only/idempotent/non-destructive, so the description correctly spends its words elsewhere: the hit shape, that spoken matches are ranked first with a snippet, that timeSec is the best moment within a fromSec–toSec window, and the PERMISSION_REQUIRED failure mode with instructions to relay it. Missing only result-count/limit or empty-result behavior.

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 dense sentences, front-loaded with the core purpose and the two-mode split before the return shape and the permission caveat. Every clause carries information, though the parenthetical example and the hits list make it slightly cramped for a single paragraph.

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 helpfully enumerates the hit fields, and it flags the permission prerequisite. It is nearly complete for a 3-param read tool; the remaining gap is what happens when nothing matches or whether an index/transcription must exist first.

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 genuinely adds query semantics the schema's 'What to look for — plain language' does not: visual queries should describe imagery while spoken queries should use exact transcribed words. That materially changes how an agent fills the `query` parameter.

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 ('Semantic search over the project's media') and immediately splits the capability into two well-defined modes: visual scope (what is IN the picture) and spoken scope (transcribed speech). This is far more than a restatement of the name and lets an agent distinguish it from retrieval siblings like get_media or inspect_media.

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 concrete guidance on how to phrase each query type ('describe a shot: aerial city at night' vs 'exact words'), which is effectively when-to-use-which-mode guidance. It also states the download prerequisite and the PERMISSION_REQUIRED relay path. It does not explicitly name alternative tools (search_stock_media, get_transcript, inspect_media), so it falls short of a 5.

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