Set ICC Plus Custom CSS

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds genuinely useful behavioral context beyond them: revision protection (concurrency guard), dry-run support (preview before applying), and integrated validation (policy-gated writes). It clearly identifies the affected field ('customCSS'), so the destructive scope is disclosed. It doesn't detail rollback or failure semantics, but the safety mechanisms are well surfaced.

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 22-word sentence that front-loads the action verbs, names the exact target field, and appends the three distinguishing features. Every phrase earns its place with zero filler or repetition of schema details.

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 destructive 6-parameter mutation tool with no output schema, the description covers the core concepts (modes, revision guard, dry-run, validation) but omits operational details an agent needs: what the return value looks like, what happens when the revision check fails or validation fails, and whether the project must be open first. Adequate conceptually, but with clear gaps at the edges.

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?

With only 17% schema description coverage, the description carries most of the burden and partially compensates: the verbs map directly to the mode enum values, and 'revision protection', 'dry-run support', and 'integrated validation' correspond to expected_revision, dry_run, and validation_policy. However, it leaves the validation_policy levels (strict vs no_new_errors vs none) and the exact revision-mismatch behavior unexplained, so compensation is high-level rather than complete.

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?

The description names multiple specific verbs (Replace, append, prepend, clear) targeting a precise resource (the official project customCSS field). The 'official' qualifier distinguishes this field-level mutation from sibling CSS tools like iccplus_css_catalog (listing) and iccplus_css_analyze (analysis), so an agent can tell them apart without opening schemas.

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 implies the operation modes via the verbs, but gives no explicit when-to-use guidance, prerequisites, or exclusions relative to siblings. It never names alternatives such as iccplus_css_analyze for validation-only workflows or iccplus_read_project for viewing current CSS, leaving routing entirely to inference.

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