media_index_get

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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation behavior: pagination is bounded, one timestamped contact sheet can be returned as an image (an MCP content-type surprise agents should anticipate), and 'a possible retake is a repeated phrase, not a quality verdict' pre-empts misreading the output. It does not cover error or staleness response 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?

Four tight sentences with no filler: action and scope first, then return shape, then prerequisite, then lifecycle rule, then the interpretation caveat. Everything is front-loaded and each sentence changes how the agent would call or read the tool.

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 six-parameter, no-output-schema read tool this is close to complete: the description covers the returned content, pagination, the image-return option, prerequisites and index invalidation. The remaining gap is sheetPage, whose paging semantics appear nowhere in the description or schema.

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 only 17% (only projectDir is documented), so the description carries most of the load. It explains indexId's provenance (from media_index), the paged read implied by limit/offset, and includePreview's effect (returns one timestamped contact sheet as an image). It leaves sheetPage and the 1-50 cap on limit unexplained.

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: 'Read a saved original-recording map in bounded pages', and enumerates what the map contains (attempts, retake groups, source timestamps, preview hints). It distinguishes itself from the index-creation sibling by requiring 'the indexId returned by media_index', so an agent knows this tool consumes an index rather than building one.

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 a clear prerequisite (must already have an indexId from media_index) and an explicit reuse/refresh rule: normal timeline edits can reuse the map, but changed source media or transcript requires reindexing. It stops short of naming an alternative read path (e.g. media_search) for agents who have no index yet, so routing is implicit rather than exhaustive.

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