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

The description adds real behavior beyond the annotations: changes persist automatically ('saves automatically') and the operation may be asynchronous (poll status). It does not reconcile with destructiveHint=true — nothing warns that 'adjust' may overwrite existing block content — and it does not state permissions or what happens to prior dashboard state, which matters for a destructive mutation.

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?

A single compact sentence with the three modes front-loaded and no filler. Minor deduction for the vague clause 'if no task', which is terse at the cost of clarity.

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 destructive, non-idempotent, possibly async mutation with no output schema, the description should say what is returned (e.g., a task/handle to poll) and which tool performs the polling. It gestures at this but leaves the polling target and returned handle implicit.

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 enum values are already explained in the schema, so the schema does the heavy lifting. The description only reinforces that 'adjust' operates on a single block; it adds no format, constraint, or prompt-content guidance beyond the schema.

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 enumerates the three modes (new dashboard, add blocks, adjust one block) that map to the `kind` enum, so the overall function is inferable. However, it never differentiates itself from the granular siblings report_create_dashboard, report_add_block and report_update_block, which appear to do the same things, leaving the agent unsure which entry point to pick.

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 only usage instruction is the cryptic 'Poll status if no task', which hints at async behavior without naming report_get_generation_status or clarifying what 'no task' means. There is no guidance on when to use this multi-mode tool versus the individual sibling tools, and no prerequisites are stated.

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