declare_out_of_band_deletion

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

With no annotations provided, the description carries the full behavioral disclosure burden. It states that the tool 'appends the tombstone with actor and reason inside the committed hash, basis out_of_band', and clarifies it is the operator's declaration, not evidence. It also mentions refusal conditions. However, it does not explicitly state the operation is a write with side effects (irreversible or requiring permissions), though 'appends' implies mutation. It also doesn't describe success output or error handling. This is a solid but not exhaustive transparency level.

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 dense but every sentence adds value—purpose, condition, behavior, and when-not-to-use. It is front-loaded with the core purpose. It is slightly long but not redundant, and the structure serves the complexity of the operation well.

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, the absence of annotations, and no output schema, the description covers the essential context effectively: the exact scenario, the alternative, and the behavioral effect. It does not describe the return value (if any) or success/failure semantics beyond refusal conditions, but these are not critical for an agent to decide whether to invoke it. It is largely complete for a niche administrative operation.

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 0%, so the description must compensate by explaining each parameter. It mentions 'actor' and 'reason' as being inside the committed hash, but does not define what they should contain or their format. 'memory_id' is never directly referenced, though it is implied as 'the record'. No parameter is explicitly described beyond its existence. This is a significant gap for a tool with three required parameters.

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 a specific purpose: handling records that were removed out-of-band (e.g., raw SQL delete, backup restore) for which a receipt exists. It distinguishes this tool from siblings like forget and verify_writes by explaining the exact scenario and the consequence of not using it. The verb 'Account' and resource (out-of-band deletion) are explicit, making the tool's function unambiguous.

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 explicitly states when to use the tool (record no longer in store due to external removal) and when not (record still present, or no receipt names it), and names the alternative (forget). It also explains the consequence of not using it (verify_writes() reports it forever). This leaves no ambiguity about selection criteria relative to sibling tools.

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