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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context: that it reads from a bank of ~249 pre-built templates, explains the effect of incluir_bloqueados, and describes the returned fields (nome, categoria, texto_html, bloqueado). This goes beyond the annotations.

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 excessively long and includes details about sibling tools (list, get) and write/delete operations, which are not relevant for this tool's invocation. This bloats the text and reduces focus. While informative, it lacks conciseness and could be streamlined to describe only the list_banco functionality.

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 complexity of 9 parameters and no output schema, the description is insufficient. It fails to document several parameters (e.g., limite, account) and does not clearly explain why patient-related parameters are present in a bank search tool. The bulk support mention is unclear. More detail is needed for complete understanding.

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?

With 0% schema description coverage, the description must compensate. It provides explanations for keyword, categoria, and incluir_bloqueados, but fails to cover limite, account, patient_id, patient_ids, manipulado_id, and manipulado_ids. The bulk support mention gives partial context for patient_ids and manipulado_ids, but it is vague and not connected to the search functionality. Overall, partial but incomplete compensation.

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 the tool reads and searches the WebDiet formula bank ('list_banco → search the WebDiet formula bank'). It distinguishes from sibling tools by explicitly describing what 'list' and 'get' do (list prescribed manipulados, get specific prescribed manipulado), making the purpose distinct and unambiguous.

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 guidance on when to use this tool (for searching the formula bank) and directs write operations to webdiet_manipulados_write and delete to webdiet_manipulados_delete. However, the mention of 'Bulk support: accepts patient_ids, manipulado_ids for batched execution' is ambiguous and might mislead about the typical use of this tool, slightly lowering the score.

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