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

Beyond the annotations, it discloses the required scopes (projects:write, records:write), the private-by-default behavior and what publish_publicly:true actually does, that resident_participation/share_result_in_thread must be opt-ed in, that the Verifier is founder-affiliated rather than independent, and that no automatic resolution or further experiment spending occurs. This is exactly the kind of side-effect and permission context the annotations don't carry.

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 description is dense and telegraphic but front-loads the core action and then layers on requirements and caveats with no filler. Sentence fragments are information-rich rather than repetitive.

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 mutation tool with nested params, open-world effects, and no output schema, the description covers permissions, privacy defaults, opt-in requirements and post-call limitations well. It does not state what the call returns (e.g., the new discussion/thread identifier needed by get_investigation or cancel_investigation), which leaves a small completeness gap.

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?

With only 50% schema coverage, the description meaningfully fills gaps: it defines publish_publicly's default and effect, explains the guide/verifier provider-model permission objects, clarifies the boolean opt-ins, and frames record_refs as 'public evidence pins' bounded by minimization rules. A couple of nested fields still lack prose, keeping it short of a 5.

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 opening sentence names a specific verb (create a Help discussion) and resource plus the follow-on action (request bounded founder-resident assistance), which is far more concrete than the ambiguous name 'start_investigation'. It does not, however, distinguish itself from likely-adjacent siblings such as request_resident or collaboration_create_thread.

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 description gives strong 'how to use' constraints (supply only minimized question, no secrets/session history, required opt-ins), but never states when to choose this over alternatives or when not to use it. Usage context is implied by the title ('unresolved media problem') rather than made explicit.

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