eds_bulk_fix_metadata

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently states that the operation is reversible, returns a single undo object, writes in a batch, requires a token, and supports dryRun and publish modes. It does not mention potential failure modes or rate limits, but the key behavioral traits are well disclosed.

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 a single, dense paragraph with no redundant phrases. Each sentence contributes essential information: purpose, input structure, batch behavior, rollback mechanism, modes, token requirement, and pairing suggestion. It is front-loaded with the primary function and efficiently covers all critical aspects.

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 (batch metadata update with rollback, dryRun/publish modes, auth token), the description covers all critical aspects: what it does, how to use it, undo capability, preview/publish behavior, token necessity, and integration with the audit workflow. The undo object is explicitly mentioned, addressing the lack of an output schema. It is sufficiently complete for an agent to invoke appropriately.

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?

The schema already covers 100% of parameters with descriptions, giving a baseline of 3. The description adds value by explaining the intended workflow (audit first, supply values, use dryRun, then publish) and clarifies the role of the pages parameter ('the agent supplies each page's values after auditing'). This helps the agent understand what data to pass and in what order.

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 tool's purpose: 'Fix SEO/social metadata across MANY pages in one reversible operation.' It uses a specific verb and resource, and differentiates from sibling tools by emphasizing the bulk aspect, single undo object, and rollback via eds_da_rollback. It also mentions pairing with eds_audit_site, further clarifying its niche.

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?

Provides clear usage context: it's for fixing metadata on many pages, requires EDS_DA_TOKEN, and is meant to be paired with eds_audit_site to fix findings. It explains the dryRun and publish modes and mentions that the agent supplies values after auditing. While it doesn't explicitly say when not to use it, the 'MANY pages' and 'bulk' language implicitly excludes one-off fixes, which are better handled by eds_fix_metadata.

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