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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: it discloses the two return link types (open_url for rehearsal, web_url for reading) and warns that role/mode selection happens in the app, not via the tool — preventing the agent from falsely promising saved rehearsals or preset settings.

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 sentences, front-loaded with the purpose before the exclusions, and every sentence serves a distinct function. It is slightly dense with stacked prohibitions in the final sentence, but nothing is wasted.

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?

An output schema exists, so return values need no description, and the annotations cover the read-only profile. The description covers source, output link types and misuse caveats; only the differentiation from get_practice_monologue and the failure mode for an invalid slug are unaddressed (the latter is covered in the locale schema description).

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 description coverage is 100%, so the schema already documents slug provenance and the locale enum/error behavior in detail. The description only restates that the scene comes from list_practice_scenes without adding syntax, defaults, or fallback semantics. Baseline 3 is appropriate when the schema carries the parameter burden.

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 — reading the exact dialogue, partner cues and roles of a published scene — and explicitly ties the input to list_practice_scenes. An agent can distinguish this from list_practice_scenes (which enumerates) and from the monologue siblings 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?

Gives clear context (scene must be selected from list_practice_scenes) and an explicit exclusion ('Do not use for private scripts'), plus caveats about what the returned link does not do. It does not, however, tell the agent when to prefer this over the sibling get_practice_monologue, so the scene-vs-monologue routing decision 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.