read_notes

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

Annotations already declare readOnlyHint=true and openWorldHint=false, yet the description adds genuinely new behavior: mute and probability are omitted from the result, and a read_notes + write_notes round trip silently resets them. That data-loss warning is exactly the kind of context annotations cannot carry. It falls short of 5 only because it says nothing about failure modes, e.g. what happens for an empty or nonexistent slot.

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?

Two tight sentences with the primary return contract front-loaded and the caveat second. Every clause carries information; nothing is filler.

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 does a reasonable job of describing the return value and its sort order, though it defers the actual record shape entirely to write_notes. The unexplained track/slot parameters are the main completeness gap for a two-required-param read 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?

Both parameters (track, slot) have 0% schema description coverage, and the description never explains whether they are indices, IDs, or zero- versus one-based. The phrase 'the clip's' implies the pair identifies a clip but adds no concrete meaning, so the description fails to compensate for the coverage gap.

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 ('return the clip's length and its notes') plus the ordering and the shape it matches, and names the sibling write_notes as the reference point. An agent can immediately tell this apart from write_notes or read_device 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?

Usage is only implied: the description hints at reading before a write_notes round trip but never states when to prefer this tool or what conditions make it inappropriate. There is no explicit when/when-not guidance or naming of an alternative reader.

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