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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond that: records are provisional, back no `tasks` row until confirmed, and `missing_date`/`missing_owner` explain why an item stalls waiting. It does not mention pagination or ordering.

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 core definition is front-loaded in the first line. The remaining paragraphs earn most of their space by explaining the provisional lifecycle, though the 'no row in tasks / doesn't appear in get_tasks' idea is stated twice, which is mild redundancy.

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?

There is no output schema, and the description ably covers the return model for a read-only list tool (provisional segments, extraction fields, confidence, db_task_id, missing_date/missing_owner). Combined with 100% schema coverage on the four inputs, an agent has enough to call it correctly; only list behavior (pagination/ordering) is unaddressed.

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% — limit, note_date, pendientes, and workspace_id are all documented in the schema, including the default and the omit-means-all behavior. The description adds nothing about parameters (the fields it names, missing_date/missing_owner/db_task_id, are return fields, not inputs). Baseline 3 is correct.

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 resource with scope: provisional tasks scraped from daily notes that have no row in `tasks` yet. It explicitly distinguishes itself from the sibling get_tasks ('por eso no aparece en get_tasks'), so an agent can route correctly 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?

The description gives strong context for when this tool is the right one — provisional items are exactly the records get_tasks will not return — and explains the lifecycle (confirmation makes `db_task_id` point to the real task). It stops short of an explicit when-to-use/when-not clause, but the alternative is clearly implied.

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