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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description adds genuinely useful non-obvious context: this creates a definition without executing anything and without incurring charges. However, it doesn't say the created function is persisted and reusable, whether the call is idempotent, what permissions or workspace scope are required, or what is returned, so the annotation-plus-description pair still leaves meaningful behavioral gaps for a mutating tool.

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?

Two tight sentences with the core effect front-loaded and no filler; the "nothing runs / nothing is charged" clause earns its place by preempting a likely misconception. It is slightly undersized for a four-parameter nested mutation, but nothing is redundant.

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 tool with four required parameters, a nested object schema, zero schema descriptions, and no output schema, the description is far too thin — it omits what spec_id/revision_id refer to, how the parameters array binds to request values, and what the caller gets back. Only the no-execution/no-charge property is fully covered.

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% across four required parameters, so the description carries the full burden and largely fails: spec_id and revision_id are never mentioned, and the nested parameter object (name pattern, paths list, prefix/suffix, value_type enum) is only obliquely gestured at by "some of its values as typed inputs." It hints that inputs bind to request values but gives no mapping between paths and value_type beyond that.

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 conveys a specific effect — "makes a saved request run once per row, with some of its values as typed inputs" — but it never uses the word "function" or says that a persisted, reusable investigation function object is being created, which is what the tool name and siblings (get_investigation_function, list_investigation_functions) imply. It distinguishes the operation from pure request execution, but not from sibling creation/listing tools.

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?

No when-to-use guidance is given: nothing says you must first have a saved request and a specific revision (the required spec_id/revision_id), nor when to create a function versus reusing an existing one or running a batch. The only usage-adjacent statement, "Nothing runs and nothing is charged," clarifies consequence, not selection between alternatives.

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