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

Goes well beyond the annotation trio (destructive/idempotent/non-readonly) by disclosing that no-op writes are skipped and reported via fieldsChanged/unchanged, that tombstoned records are refused, that cross-project references are validated, and that the force override is audit-logged. These are exactly the mutation-behavior details annotations cannot express.

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?

Field inventory is front-loaded, followed by behavioral rules in descending order of importance (no-op detection, tombstone refusal, conflict handling). Six dense sentences with no filler, despite the run-on paragraph form.

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 destructive, 9-parameter mutation with no output schema, the description supplies conflict, idempotency, and no-op semantics plus the fieldsChanged reporting shape. It omits permission/scoping requirements and any mention of what the full response contains beyond the change report.

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 only 22%, but the description compensates: it names the patchable fields, explains storyId's ticket-key/UUID format and project constraint, and states the global null-clears semantics for nullable params. It leaves severity/status enum meanings and the semantics of an omitted (vs null) field to the schema and inference.

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?

Opens with a specific verb and resource ("Patch fields on an existing defect") and enumerates the exact patchable fields, which immediately separates it from create_defect, delete_defect, and the story-update siblings. An agent can identify the target resource and scope without opening the schema.

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-to guidance: pass null to clear a nullable field, use force:true only after re-reading with get_defect, and expect refusal on tombstoned defects. It does not explicitly route to alternatives (e.g. restore_defect for soft-deleted records, or update_story for non-defect entities), leaving that inference to the agent.

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