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

The description includes a critical warning: 'Altera dados de PRODUÇÃO (o Bsoft não tem homologação)' - which is a significant behavioral disclosure beyond the annotations. The annotations only say readOnlyHint=false, destructiveHint=false, and no other hints. The description also explains that it alters production data, which is a key behavioral trait. It also mentions that it supports bulk operations with ids/parent_ids. This adds valuable context beyond what annotations provide.

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 fairly concise, with a critical warning at the beginning, followed by usage instructions and a resource list. It's front-loaded with the warning about production data, which is important. The resource list is long but necessary. The mention of 'Flattened action: delete' and 'Bulk support' at the end is a bit redundant with the schema, but adds some value. Overall, it's well-structured and not overly verbose.

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?

The tool is complex with 7 parameters and no output schema. The description covers the key usage patterns (update/patch/delete require id, nested resources require parent_id, bulk support) and the production warning. It lists resources, which is helpful. However, it doesn't explain what the body should contain or any constraints on the resources. It also doesn't explain the 'account' parameter. Given the complexity, the description is reasonably complete for a delete tool, but could be more detailed.

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?

The schema description coverage is 0%, meaning the description does not explain the parameters at all. The schema lists 'resource', 'id', 'ids', 'body', 'account', 'parent_id', 'parent_ids', but the description only mentions some of them: resource, action (not a parameter), body, id, parent_id, and ids. It also mentions 'create_lote' but that's not a parameter. The description partially compensates by explaining the usage of id and parent_id, but it doesn't explain 'account' or 'ids' or 'parent_ids' in detail. Since the schema has 0% coverage, the description should compensate more, but it only touches on some parameters. Baseline would be 1 or 2, but it adds some meaning for id and parent_id, so I'll give a 3.

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 clearly states that this tool handles write operations in Bsoft TMS (create/update/remove), but the tool name ends with '_write_delete' and the flattened action is 'delete', which suggests a specific delete operation, while the description covers a broader write set. The verb is implied by the name and the flattened action. The description lists resources, which is helpful. It distinguishes from siblings by the resource list and the note about production data. However, the description starts with a broad 'cria/atualiza/remove' which is ambiguous and could confuse an agent expecting a delete-specific tool. The flattened action clarifies it, but the mismatch between description and name is a minor issue.

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 provides explicit usage: 'Passe resource, action e body (JSON)' and states that update/patch/delete require 'id', nested resources require 'parent_id', and create_lote sends a list. However, it doesn't explicitly say when to use this tool vs the other write tools (create, patch, update) except by the action parameter. The flattened action is delete, which implies this tool is for deletion, but the description says it covers all write operations. There is no explicit 'when not to use' or alternatives mentioned. The sibling tools are similar, so this could be ambiguous.

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