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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds non-obvious behavior the annotations cannot express: a class of rows is silently protected and requires an explicit force flag, with a documented preferred remediation path. It does not state error behavior when the id is missing or unknown, which keeps it off a 5.

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?

Two sentences, no filler, with the core action front-loaded and the protection caveat immediately after it. Every clause carries information an agent needs before calling.

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 two-parameter destructive mutation with no output schema and full annotation coverage, the description supplies the essential context: scope, protected-row semantics, and the preferred alternative. Only the failure mode (unknown or already-deleted id) is unaddressed, a minor 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 the baseline is 3. The description nonetheless adds real meaning to force by explaining what it overrides (document-extraction and CSV-import provenance) and by signaling that using it is not the normal path, which the schema's one-line description does not convey.

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?

"Delete one observation by id" gives a specific verb, resource, and cardinality, so it is clearly distinct from the other vora_delete_* siblings (biomarker, condition, mood, symptom) and from vora_list_observations. It stops short of explicitly naming a sibling to route away from, so it is clear rather than fully differentiating.

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 goes beyond "when to use" to give the correct alternative route: rows from document extractions or CSV imports are protected unless force=true, and the recommended path is deleting the document or rolling back the import in Vora. That is an explicit condition plus named alternative, which is exactly what an agent needs to avoid a failed or wrong call.

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