delete_object

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds real substance beyond them: irreversibility, the fact that references are NOT cleaned up, and a concrete example (a person still referenced by a family). That is exactly the extra context an agent needs before a destructive call.

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?

Front-loads the action and the destructive nature in the first two lines, with the caveat and remediation guidance after. The sentence on dangling references is somewhat long but each clause carries actionable information; little waste overall.

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?

With a small two-parameter schema, full schema coverage, no output schema, and annotations covering the safety profile, the description is nearly complete for correct invocation. It could still mention whether the object handle becomes invalid or whether an undo exists, which would close the remaining gap.

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 coverage is 100%, so both parameters and their accepted identity forms are already documented in the schema. The description's 'handle or gramps_id' phrasing restates the schema rather than adding new semantics, so baseline 3 applies.

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?

States a specific verb (permanently delete) and resource (object from the tree) plus the two accepted identifiers (handle or gramps_id). The warning about dangling references implicitly distinguishes it from detach_object, but no sibling is named explicitly, so an agent must infer the boundary.

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?

Gives concrete when-not guidance: prefer deleting leaf objects and detach references first where possible. That steers the agent away from this tool in the risky case, though it never names detach_object or merge_objects as the literal alternatives.

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