text_manage

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

destructiveHint=true is the only annotation, and 'Edits' is consistent with it, so no contradiction. The description adds the useful nuance that structure is preserved only in the preserve mode, but says nothing about the expectedRevision optimistic-concurrency requirement, workspace scoping, or that content is replaced rather than appended.

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?

A single front-loaded sentence with no filler, and the verb and resource lead. It is dense with jargon ('bounded plain-text segments') but every clause earns its place.

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?

Wait—output schema exists so return values need no explanation, and the schema fully documents parameters. What remains missing is concurrency and sibling differentiation, which is a real gap for a destructive mutation tool in a crowded text-tool family.

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 reported at 100%, so the schema itself carries the parameter burden and the baseline of 3 applies. The description adds conceptual context for segments vs. tspans but names no parameters, enums, or formats beyond what the schema defines.

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 (Edits) and resource (local SVG text) and even names the two editing styles, 'bounded plain-text segments' and 'explicit multiline tspans', which map to the two oneOf modes. It does not, however, differentiate itself from text-adjacent siblings such as text_path_manage, flowed_text_convert, or text_to_paths.

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?

'preserving existing structure only when requested' implies a mode-selection rule but never states it explicitly, and there is no guidance on when to reach for this tool rather than elements_update or the other text tools. Usage is inferable rather than stated.

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