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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: the response is deliberately lossy (look inheritance, clips list only diffs, missing end/source-out/name fields, keyframe counts instead of lists), which prevents misreading the data. It says nothing about response size, latency, or permissions, so it stops at a solid 3.

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?

Purpose and the 'Start here' directive are correctly front-loaded, and almost no sentence is filler. However the compact-mode explanation is written in a dense telegraphic register ('source out (in + duration × speed)') that is harder to parse than necessary and buries the two most important facts, lossy output and the detail escape hatch, mid-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 has to describe return values itself, and it does: field-omission rules, keyframe-as-count, media being basics-only with status only when not ready, and what detail:true expands. The main gap is the unexplained trackId and includeClips parameters, which affect the very response shape being described.

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 25% (only projectId is documented), so the description must carry the load. It explains 'detail: true' well and ties it to remove_keyframe's need for keyframe times, but trackId and includeClips are never mentioned and their effect on the response is left to inference.

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?

The opening sentence enumerates the payload concretely: project settings, tracks with clips, media, and transcript status, which is enough to distinguish it from siblings like list_media or get_transcript. The verb is implied by the name rather than stated, and 'Get project' vs 'open_project'/'list_projects' differentiation is left partly to the reader, keeping it short of a 5.

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?

'Start here' is an explicit entry-point instruction, and the description names the alternative path for media detail ('list_media adds tags and loudness') plus the escalation path ('detail: true gives every clip in full'). There is no explicit when-not guidance, 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.