eds_fix_audit

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

With no annotations provided, the description carries the full burden. It discloses that the operation is reversible via eds_da_rollback, that everything is pushed in a single batch, that dryRun previews without writing, and that publish:true makes it live. It also notes the EDS_DA_TOKEN requirement. These go beyond basic parameter info and set clear expectations for the agent.

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?

The description is comprehensive yet succinct. It front-loads the core purpose, then explains the workflow, safety, and prerequisites. Each sentence adds value—no redundant or vague phrasing. The length is justified by the tool's complexity and the need to convey safety features.

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?

Given the tool's complexity (multiple parameter types, batch behavior, publish vs dryRun), the description is complete. It covers the expected input, the reversible nature, and prerequisites. There is no output schema, but the description sufficiently explains what happens during dryRun vs publish, so the agent can anticipate results.

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?

Although the schema already describes each parameter (100% coverage), the description enriches them with usage context: metadata fixes are per-page, redirects use { source, destination }, and values must come from findings. It clarifies the semantic difference between dryRun and publish, and that metadata only changes provided fields. This adds meaning beyond the raw schema.

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 clearly states the action: 'Fix what the audit found — across metadata AND redirects — in ONE reversible operation.' It identifies the resource (audit findings) and distinguishes itself from sibling tools like eds_fix_metadata and eds_fix_redirect by combining both. The workflow ('audit → you supply values → one safe, reversible apply') further clarifies its specific role.

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?

Explicitly specifies when to use: 'After eds_audit_site/eds_audit_report, findings that carry a `fix` are repairable here.' It states that the tool does not invent copy, implying the user must provide values from findings. It also contrasts with alternative tools and explains the dryRun and publish parameters as part of the safe workflow.

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