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

The annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is supplied structurally. The description adds the useful constraint that deletion should be user-initiated, but says nothing about irreversibility, what happens with an unknown or already-deleted snippet_id, or what is returned on success — context the annotations don't cover.

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 waste: the action and its target come first, the safety caveat second. Nothing needs to be re-read or untangled.

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 single-parameter, non-idempotent-sensitive mutation whose destructive and idempotent traits are already fully declared in annotations, the description covers the essentials an agent needs to call it correctly. Only the post-deletion behavior is left implicit, which is a minor gap given there is no output schema.

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% and the single parameter's schema text ("ID del texto (de list_saved_texts)") already explains origin and type constraints. The description only repeats the provenance pointer, adding no format, lookup, or validation detail beyond the schema, 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 names a specific verb+resource ("Borra un texto") and grounds it in "list_saved_texts", so an agent knows exactly which object family is affected and where the ID comes from. It doesn't explicitly contrast with create_saved_text or update_saved_text, but the delete verb plus the target list is enough to separate it from the other saved-text siblings.

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?

"Úsala solo cuando el usuario lo pidió" is a real usage guardrail: it warns the agent not to delete proactively or speculatively. However, it names no alternative (e.g., update_saved_text for edits) and gives no condition for what to do when the user's intent is ambiguous, so the guidance is implied rather than complete.

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