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

Goes far beyond the readOnly/destructive annotations: discloses pagination via next_cursor/has_more, silent filter ignoring echoed in ignored_filters with unsupported_query coverage status, unknown object types returning valid types, per-object sort orders, and that nothing is sent (consistent with readOnlyHint=true). The unsupported_query warning is exactly the kind of failure-mode disclosure that prevents a wrong answer being reported as fact.

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?

Dense but nearly every sentence carries operative information for a genuinely complex tool; the purpose leads and behavior follows. Minor deductions: the when-to-use section and example sit at the tail rather than up front, and several distinct topics (sorting, opportunity fields, projection) run together without visual separation.

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?

Given 6 parameters, nested filter objects, and a high-stakes silent-failure mode, the description covers routing, pagination, error semantics, ordering, and object-specific quirks. Return fields are restated even though an output schema exists, but that repetition is harmless and the coverage is complete 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 100%, so the baseline is 3, but the description adds genuine meaning: projection 'actions' semantics for tasks (sequence steps, deduped reminders, exact counts plus paged rows), the write-with-taskId/enrollmentId caveat guarding against using projection ids as write targets, and how filters behave when unsupported. The limits parameter and cursor mechanics are left to the schema, which is fine.

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+scope: "List/filter any object" with built-in typed filters, and immediately distinguishes what it is not by routing report-shaped questions to run_report. An agent can tell it apart from get_record, run_report, and read_changes without opening a 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?

Explicit when-to-use clause ("a plain list — open tasks, deals in a stage, contacts at an account — before run_report") with the alternative named and the selecting condition. It also gives operational directives — follow every page, fix inputs before claiming matches or none — which prevent the most likely misuse of a paged, filter-silently-ignoring endpoint.

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