opencdr_detection_backfill_status

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower; the description still adds a genuinely useful semantic caveat that a completed retained-source scan does not prove complete history. Against that, it refers to 'next_after', a parameter that does not exist in the schema (the schema has 'after'), which undermines confidence in the behavioral account. No statement about pagination behavior or output shape beyond the fragmentary hint.

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?

Sizing is reasonable, but the first sentence is grammatically tangled ('a backfill plan/progress or bounded outcomes and skipped-source findings') and the line breaks fragment what should be a coherent paragraph. The reference to a nonexistent 'next_after' parameter spends words on something the agent cannot act on.

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?

Five parameters at 0% schema coverage, one of them required, with no output schema to fall back on, puts a heavy disclosure burden on the description, which it only partly meets. An agent still cannot tell what opencdr_detection_backfill_status returns by default, how results=true changes the payload, or what limit/after do.

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 0%, so the description carries the full burden, and it only clarifies one of five parameters (agent_id, fleet vs core mode). The required job_id, as well as limit and after, get no explanation, and the mention of 'next_after' names a parameter that is not in the schema, actively misdirecting the caller.

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 opening clause 'Inspect a backfill plan/progress or bounded outcomes and skipped-source findings' gives a verb and a resource, but the 'or' hedges together three different views, so an agent cannot tell exactly what a single call returns. Nothing distinguishes it from siblings such as recovery_status, handoff_status, or consumer_status, all of which plausibly also report job progress.

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 does give conditional guidance: 'In fleet mode, supply agent_id explicitly. Core mode leaves agent_id unset,' and it says to use results/next_after to review invalid, expired or conflicting source records. However, it never states when to call this versus the other *_status siblings, and no exclusions or prerequisites are offered.

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