Inspect Session Transcript

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

Discloses read-only behavior (consistent with readOnlyHint annotation) and describes return content (full message history, metadata). Adds value beyond annotations by detailing the output structure and confirming no mutation.

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?

Three concise, well-structured paragraphs. First paragraph defines purpose and output, second lists companion tools, third provides use case and safety note. Every sentence is purposeful; no redundancy.

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?

Despite no output schema, the description adequately explains return values (message history, metadata). With only one parameter and clear annotations, the description covers purpose, usage, behavior, and parameter requirements completely.

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 baseline is 3. The description reinforces the critical token suffix requirement and warns against stripping it, adding practical guidance beyond the schema's pattern and description.

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?

Clearly states the tool views a session's conversation transcript and metadata. Lists specific outputs (full message history, workflow step, cloud, etc.) and distinguishes itself from siblings by naming companion tools (convostatus, tfruns, stackversions).

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?

Explicitly tells when to use (e.g., 'what did I say earlier?', retracing session state) and when not (it's read-only, never mutates). Names alternatives and complementary tools, providing clear context for selection.

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