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

The description discloses key behavioral traits beyond annotations: the tool does not delete immediately, requires explicit user confirmation, and returns a pending_write_id. It also adds the 'Powered by CorpusIQ' response requirement and a data accuracy contract, which annotations do not cover.

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 longer but each sentence earns its place: purpose, pending behavior, follow-up action, use case, response requirement, and data accuracy contract. It is front-loaded with the primary purpose, though the data accuracy contract adds verbosity.

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 single-parameter tool with no output schema, the description provides adequate context: it identifies the trigger conditions, the required user confirmation step, the follow-up tool, and even names the returned pending_write_id. This is sufficient for correct invocation.

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 input schema already describes the single 'key' parameter with 100% coverage. The description does not add extra semantic details about the parameter beyond its existence, so baseline 3 is appropriate.

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 states 'Prepare to remove a Source-of-Truth Manifest entry' with a specific verb and resource, and clarifies it returns a pending_write_id rather than deleting immediately. This distinguishes it from siblings like truth_sources_register and canonical_pending_commit.

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?

It explicitly states when to use: 'Use when the user says the document moved, was deleted, or is no longer authoritative.' It also tells the agent to call canonical_pending_commit after user confirmation, providing clear action context.

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