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

The description discloses beyond annotations: it states billing ('Billed for retried work'), the condition of failed_expertises, the re-run and re-billing scope for failed domains only, and that the record stays attributed to its original model. It also tells the agent to poll get_job_status and re-read get_record. Annotations only set readOnlyHint=false and destructiveHint=false; the description adds substantial behavioral context without contradicting them.

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 each sentence earns its place. It front-loads the core function, then presents prerequisites, parameter guidance, return value, and alternatives succinctly. There is no fluff or repetition; it is an efficient, well-structured text.

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 (6 parameters, nested object, output schema), the description is complete: it specifies the required inputs, the output handling, the alternative path when no record exists, and links to further recovery docs. It covers all aspects an agent needs to invoke the tool correctly without guessing.

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, but the description enriches parameter meaning significantly: it tells the agent to supply entity_input_data and saved_schema_id from get_record, explains the model parameter's default behavior and when to override it, and clarifies that schema_id can be replaced by target_schema. This goes beyond the schema's field definitions and guides correct invocation.

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 a specific verb and resource ('Retry only an existing record's failed expertise domains') and clarifies that it operates on failed domains only, distinguishing it from sibling tools like enrich_entity and merge_records by explicitly mentioning those alternatives. It also names the output (job_id) and the follow-up steps.

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 this tool (when a record has failed expertises) and when not ('a surviving successful sibling is not retryable and returns no_failed_expertises'). It names concrete alternatives for the no-record case ('use a one-model enrich_entity with database_sync=false followed by merge_records instead') and directs to a documentation link for recovery decisions. This leaves nothing to inference.

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