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

readOnlyHint=true already tells the agent this is a safe read, and the description adds real value beyond that: it discloses result granularity (one row per deletion lote, not per movement) and that each row carries a count and a purge date. That return-shape information is meaningful since there is no output schema. It omits whether anything is filtered or capped.

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?

A single sentence with no filler, front-loading the resource ('Deleted bank movements still recoverable') before the row-shape detail. Every clause carries information the schema and annotations do not.

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 zero-parameter read tool with no output schema, the description covers what is listed, the level of aggregation, and one key field (purge date) — enough to call it correctly. It stops short of describing whether results are grouped, paginated, or bounded, which would complete the picture.

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 tool takes zero parameters, so the baseline of 4 applies. The description makes no parameter claims and needs none, and the empty schema is self-evident.

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 precisely what the resource is: deleted bank movements that are still recoverable, with one row per deletion batch (lote). Combined with the tool name, an agent knows this is a trash-listing read. It does not explicitly contrast itself with restore_bank_trash or delete_bank_transactions, so sibling differentiation is only implicit.

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 phrase 'still recoverable' implies this is the discovery step before calling restore_bank_trash, but no explicit when/when-not guidance or named alternative is given. Usage is inferable rather than stated.

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