run_report

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

With no annotations, the description carries the full burden and mostly delivers: it says the click fills the spreadsheet ON THE SERVER, sets PF_LAST_ACTION="PF_RUN_REPORT", and that cell content ships as a 1C-packed binary .mxl blob (not strings, not zlib) so per-cell reading is deferred. It omits preconditions (attached test client, required open form) and permission needs, keeping it from a 5.

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 lead sentence is front-loaded and correct, but the body is a dense wall of low-signal detail — raw hex byte offsets ('88 82 81 20 20 20'), .mxl format lore, and parenthetical asides — that outweigh the actionable content and make the description hard to scan.

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?

An output schema exists and return values are also stated, so that burden is covered. But for a relatively complex native-run tool, the definition never states prerequisites (which client/form must be active) or failure behavior, leaving a meaningful gap for correct invocation.

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 0% for all 4 parameters. The description only gestures at two of them ('setup from capture', the PF_RUN_REPORT default for command) and never explains host or port, so it does not compensate for the documentation gap.

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+resource ('Run a report / fill a ТабличныйДокумент natively') and even names the mechanism (a FORM-COMMAND click in the click_command family), so an agent can place it against siblings. It stops short of 5 because the purpose is buried under internal implementation detail and never crisply contrasts itself with run_scenario or a direct click_command call.

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?

'Replays the genuine setup from capture + the command click' is the only usage hint, and it is told to verify via capture_screenshot or the PF_LAST_ACTION marker. There is no explicit when-to-use / when-not-to-use versus click_command or the other run_* tools, so an agent must infer that this is the report-specific path.

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