get_interaction_diagnostics

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

With no annotations, the description carries the full burden and does so well: it discloses session-local retention (ten minutes, 100 results, 16 MiB total, 1 MiB per result), that expired, evicted, or restarted results are unavailable, and that compact output is not redaction of private UI text or errors. These are exactly the failure modes and privacy caveats an agent needs before calling.

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?

Five tight sentences, front-loaded with what the tool reads and its no-replay guarantee, then the identifier mapping, then retention limits, then the privacy caveat. No sentence is filler and nothing is repeated.

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 two-parameter read tool with no output schema, the definition covers sourcing of inputs, availability window, and the nature of returned content (UI text, errors, non-redacted). It stops short of describing the shape or size of the returned record beyond the 1 MiB per-result cap.

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 0% and both parameters are bare UUID strings, so the description must compensate. It does by telling the agent to source the values from diagnostics.session_id/result_id, which explains where the identifiers come from rather than just naming them; it does not clarify whether the pair must be mutually consistent or which wins on mismatch.

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 ('Read') and a specific resource ('retained original interaction or journey result'), and negates two plausible misreadings (replaying input, observing the device). It never names a sibling such as run_journey or capture_debug_snapshot, so the agent must infer differentiation from the negations alone.

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?

Implied guidance is present: this is the path for inspecting a prior result without re-running it, and the retention rules tell the agent when a call will fail. There is no explicit when-to-use vs when-not-to-use statement relative to siblings that also expose execution data (get_logs, capture_debug_snapshot, run_journey).

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