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

Annotations already declare readOnly=false, destructive=false, idempotent=false; the description adds genuinely new behavior — new rows land status='unapproved' — plus the two response conditions an agent must handle. It does not cover permission/auth requirements or what happens on partial failure, so it is strong but not exhaustive.

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?

Workflow position is front-loaded, then per-parameter meaning, then response handling — each sentence earns its place and the parameter block is compact rather than padded. No redundancy with the annotation block.

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 an output schema exists, return values need not be re-specified; the description instead supplies what the schema cannot — the unapproved-row state and the required agent handling of validation_errors and near_duplicates. Nothing an agent needs to call and follow up correctly is missing.

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 carry the burden, and it does: `memory` is the slug, `results` maps each pass `key` to that pass's JSON with a concrete example ({"classes": {...}, "objects": {...}}), and `source_doc` is an optional provenance label. All three parameters are given meaning absent from the schema.

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+resource ("Save the extraction you produced") and situates it precisely in the workflow relative to siblings get_extraction_prompt and resolve_names. An agent can distinguish it from merge_objects, list_unapproved, and resolve_names without opening any 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?

Explicitly declares it is the LAST step after get_extraction_prompt and exactly one resolve_names call, and routes follow-up work: report validation_errors to the user, review near_duplicates and fold confirmed pairs with merge_objects. Both when-to-use and when-to-follow-up-with-an-alternative are named.

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