symbols_manage

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

The single annotation (destructiveHint=true) is consistent with the delete action, and the description adds real behavioral context beyond it: cyclic or missing use references are rejected. However, it omits other important traits — that mutations require a matching expectedRevision, that clones are positioned locally, and any workspace/permission scoping. Useful but incomplete.

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 tightly packed sentences, front-loaded with the operation set and ending with the rejection behavior. No filler, no restatement of the title or name.

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 four-action mutation tool with a complex oneOf schema, an output schema, and revision-based concurrency, the description covers the operation set and one error case but leaves the expectedRevision requirement and the distinction among the four variants unstated. Adequate but with meaningful gaps given the tool's complexity.

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 structured schema carries the burden and a 3 baseline applies. The description names the actions and hints at positioning for clones, but adds nothing about expectedRevision semantics (a revision token for concurrency control) or the required spec fields (id, sourceId, viewBox), which the schema lists without explanation.

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 specific verbs and resource: 'Lists, creates or deletes reusable SVG symbols and creates positioned local use clones.' This maps cleanly to the four action variants (list/create/delete/clone) and clearly distinguishes it from neighbors like masks_manage or patterns_manage by naming symbols. It stops short of 5 only because it does not contrast itself against the closest sibling (defs_vacuum, which would remove unused defs).

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?

The description says what happens with invalid references ('cyclic or missing use references are rejected') but gives no when-to-use guidance, no mention of the optimistic-concurrency prerequisite (expectedRevision on create/clone/delete), and no routing to alternatives such as defs_vacuum or patterns_manage. An agent gets no help deciding when this tool is the right choice.

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