company_session_understand

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

No annotations are provided, so the description carries the full behavioral burden. It says 'Build' but does not disclose whether the operation persists data, whether dry_run avoids writes, whether existing data is replaced or merged, or what side effects an agent should expect.

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 one sentence with no wasted words and front-loads the action and result. It is terse to the point of thinness, but it is still properly concise.

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 an 11-parameter tool with no annotations, no output schema, and no parameter descriptions, this is not enough context. The description does not define what 'normalized' means, what the output structure looks like, whether calls are safe to repeat, or what the expected return behavior is.

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%, and the single clause does not compensate for 11 parameters. 'JSONL evidence' only loosely maps to evidence_id/source_type; it gives no guidance for dry_run, clearance, tenant_id, max_events, groups_json, projects_json, or session_native_id.

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 names a specific action ('Build'), specific output objects ('normalized sessions, episodes, and cited candidates'), and a specific input ('JSONL evidence'). This is enough to separate it from list/search/propose siblings such as company_memory_propose_from_evidence and company_episodes_search.

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?

'From JSONL evidence' implies the tool is intended for ingesting raw session/evidence data, so there is a light usage hint. There is no explicit statement of when to use this tool over sibling options, when not to use it, or required prerequisites.

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