analysis_delivery_collapse_diagnose

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

With no annotations, the description carries the full burden. It transparently discloses that the tool is read-only, may return most_likely_cause=null when no cause is implicated, always reports open questions and limitations, and shares a concrete incident where every check passed yet the cause was never found. This is unusually honest and complete for behavioral disclosure.

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 longer than two sentences but every sentence adds value: purpose, method, outputs, behavioral caveats, and next steps. It is front-loaded with the main action. A slightly tighter structure could be imagined, but the density is warranted for a complex diagnosis tool.

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 no output schema, the description adequately explains return values (timeline, changes, checks, cause with evidence, open questions, limitations). It also situates the tool across platforms and explains how to use follow-up evidence tools. This is complete for the tool's complexity.

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%, so the baseline is 3. The description adds workflow context by explaining how the evidence parameter maps to elimination-ladder checks, how changes overlays delivery, and how timeline_days/change_lookback_days control the analysis window. This goes beyond pure schema definitions, justifying a 4.

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 opens with a specific verb and resource: 'Diagnose one collapsed campaign.' It clearly defines the method (overlay change feed on delivery, fold in elimination-ladder evidence) and distinguishes itself from siblings like analysis_delivery_collapse_check by focusing on diagnosis of a single campaign with a causal analysis approach.

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 clear context: use after gathering elimination-ladder evidence, and calls for read-only diagnosis. It explicitly instructs to 'gather evidence with the per-platform tools it names in next_checks and call it again.' However, it does not explicitly mention when not to use it or contrast with sibling diagnostic tools like analysis_delivery_collapse_check, so it stops short of a 5.

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