Info

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

Annotations already carry the full safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description only needs to add context, and it does: "native state" signals raw, unprocessed model data, and "points as t/y" discloses the envelope coordinate format. It adds nothing about volume of data returned, performance cost of the "full catalogue" option, or whether output is a snapshot versus live state.

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?

One sentence, front-loaded with the verb "Read native state" and then a clean parallel list of selectable subjects, with parenthetical detail only where genuinely needed. No filler, though the asymmetry of annotating just two of nine enum values slightly undercuts the structure.

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?

For a single required enum parameter with no output schema and annotations already covering safety, this is close to sufficient: it names every selectable subject and hints at return shapes (t/y points, command catalogue with parameters). The remaining gap is that no return-shape hint exists for the majority of enum values, which matters since there is no output schema to fall back on.

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 0%, so the description must compensate, and the single parameter is an enum whose values the description essentially reproduces. It does add real meaning for two values — "Envelopes (points as t/y)" and "Commands (full catalogue with parameters)" — which tell the agent what payload shape to expect, but the other seven values get no such clarification beyond their bare names.

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?

"Read native state" gives a specific verb plus an enumerated set of resources (Tracks, Clips, Envelopes, Labels, Boxes, Selection, Preferences, Commands, Menus), so the agent knows it is a generic state-reader. It stops short of 5 because it never distinguishes itself from look-alike siblings such as audacity_project_info, audacity_preferences, audacity_menus, or audacity_command, which appear to cover subsets of the same ground.

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?

There is no explicit when-to-use or when-not-to-use guidance; the reader must infer that this is the inspection tool from the word "Read". With siblings like audacity_project_info and audacity_preferences present, the definition offers no rule for choosing between them, which is exactly where guidance would matter most.

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