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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds genuinely new behavioral context: the two response modes triggered by presence/absence of the type argument, plus an emphatic 'exact' vocabulary hint that matters when authoring calls.

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 tight sentences, no filler. The purpose is front-loaded, the branch behavior follows, and the 'read before authoring' call to action closes it. Every sentence carries information an agent acts on.

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?

No output schema exists, but the description compensates by describing the return shape in both modes (name/description list vs. JSON Schema for one op). For a single-optional-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 goes further by explaining what happens in each branch (omit -> compact list of names and descriptions; pass type -> only that operation's JSON Schema) and by echoing a concrete example value (captions.fromComposition). That is meaningful semantics beyond the schema text.

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: 'Discover the exact CompositionOp vocabulary accepted by apply_composition.' Crucially, it names the sibling that consumes this vocabulary (apply_composition), so an agent can immediately distinguish this introspection tool from the mutation tools around it.

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 clear context ('Read this before authoring edits or captions') and the routing rule to apply_composition. It does not state any when-not condition or exclusion, but for an introspection helper with a single obvious consumer, the guidance is effectively complete.

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