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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds context beyond that: a 60-row pagination cap, the fact that results can be narrowed by range/kind/lane, and the read-after-edit pattern. It stops short of stating ordering or what happens when offset exceeds the row count, which keeps it below a 5.

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 verb and the returned columns, then usage, then exclusions, then return shape and relatives — all in five sentences with no filler. Slight deduction for the compressed clause "60 rows a read, or only fromMs–toMs, a kind or a lane," whose telegraphic phrasing takes a second pass to parse.

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?

Even without an output schema, the description names the payload keys (clipCount, totalDurationMs, timeline, tracks, transitions, markers), states the pagination limit, and lists the downstream edit tools that consume the returned handles. For a six-parameter read tool, an agent has everything needed to call it correctly.

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 adds real meaning: fromMs–toMs is a range filter, kind and lane are single-value narrowers, and offset drives pagination across both rows and markers. That resolves ambiguity the terse schema text ("From (ms).") leaves open, though it never explains the offset unit interplay with the 60-row cap.

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?

Names a specific verb and resource ("Read the timeline as a table") and immediately enumerates the exact columns returned (id handle, kind, label, lane, start/end/dur, trim, speed). It explicitly distinguishes itself from siblings that answer different questions (watch_clip, get_clip_transcript), so an agent can route without opening the 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 explicit when-to-use instructions ("Use first, and again after the person may have edited, for the handles every edit tool takes") and an explicit when-not-to-use with the named alternatives. Nothing about selecting this tool 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.