list_process_instances

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered by structured data. The description adds value beyond that: it discloses the tenant-wide scope, the default sort order (most recent first) and the shape of each row (processo, situação, etapa atual, dono). It does not mention paging behavior or a default page size, which is the remaining gap.

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?

Two short sentences with zero filler: scope, ordering, returned fields, filters, then the pointer to the sibling. The most decision-relevant information (what it lists and in what order) is front-loaded.

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 read-only list tool with rich annotations and no output schema, the description supplies the returned-field list that would otherwise be unknown, plus ordering and tenant scope. Pagination semantics (the next_before cursor cycle) live only in the schema, so an agent must open the schema to page correctly.

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 75%, so the baseline is around 3, but the description earns an upgrade by restating the two meaningful filters in domain terms ("só abertas/encerradas" maps to open, "uma definição" maps to definition_key). Limit and before are left entirely to the schema, and limit has no description there, which keeps this from a 5.

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 and resource ("Lista as instâncias (execuções) de processo"), adds the tenant scope ("da EMPRESA"), the ordering ("mais recentes primeiro") and the fields returned. It explicitly names the sibling get_process_instance as the drill-down counterpart, so an agent can separate the two without opening either 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?

"Para ver por dentro: get_process_instance" gives an explicit alternative and the condition that selects it, and the filter sentence signals the available narrowing options. It stops short of stating exclusions (e.g. when to use list_process_definitions instead, or that this returns executions rather than definitions), so usage context is clear but not fully framed.

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