apply_retention_policy

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

No annotations are provided, so the description carries the full burden. It is a potentially destructive mutation (DELETE/ARCHIVE actions) yet the description says nothing about permissions, reversibility, scope, or the dry-run capability exposed in the schema. Only the bare purpose is conveyed.

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 single sentence is efficient with no wasted words, but it is under-specified rather than genuinely concise given the tool's destructive nature and multi-parameter schema. Minimal but not wasteful.

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 destructive retention tool with no annotations, no output schema, and a nested policy array including an action enum, the description is far too thin. An agent lacks the behavioral and safety context needed to invoke it responsibly.

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 100%, with dryRun, policies, and connectionName documented in the schema itself. The description adds no meaning beyond this, so the baseline of 3 applies.

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 gives a specific verb ('Aplica') and resource ('políticas de retenção de dados'), which is clear and non-tautological. However, it does not differentiate from closely related siblings such as archive_old_data or drop_partition, so an agent cannot tell which retention-oriented tool to pick on purpose alone.

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?

There is no guidance on when to use this tool versus alternatives like archive_old_data or drop_partition, nor any prerequisites or exclusions. The description only states the function, leaving the agent to infer the context entirely.

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