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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds real behavioral context: per-block failure isolation (ok=false with error while other blocks still return data), a 500-row-per-block cap, and the filter precedence chain (report defaults → saved filters → `filters`). The 'decision-support material for a human reviewer' caveat is a useful framing signal about how much weight to put on the numbers.

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 definition repeats itself: the opening line and the second paragraph both say 'run a saved report and return its rows,' and the 500-row limit is stated twice. Front-loading the verb and resource is good, but roughly a third of the text is restatement rather than new information.

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?

With an output schema present and every parameter documented, the description only needs to cover execution semantics, and it does: partial failure, row caps, filter precedence. Nothing essential for a correct invocation is missing, though the lack of sibling routing is the one remaining hole.

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 coverage is 100%, so baseline is 3; the description earns above that by documenting filter merge order and the per-run-only scope of `filters`, which the schema does not state. It does not add anything for `conversation_id` or `merchant_id` beyond what the schema already says.

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 verb and resource: run a saved custom report and return each block's rows, with the aggregation level and 500-row cap made explicit. It is distinguishable from get_report/preview_report/create_report by the 'run and return rows' framing, though it never names those siblings to draw the boundary explicitly.

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?

Usage is implied rather than prescribed: `draft` hints at editing permission, `block_id` at partial runs, and `filters` at per-run overrides. There is no explicit guidance on when to use run_report versus preview_report, get_report, or generate_interview_report, so an agent must infer the routing from names alone.

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