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

With no annotations, the description carries the full burden and does disclose two real behavioral facts: a valid Key is required and anonymous access is disabled, plus the default 30-day window when from/to are omitted. It stops short of stating read-only semantics, pagination/limits, or error behavior.

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 sentences, front-loaded with the returned metrics, then parameters, then usage routing. Every clause earns its place with no restatement of the tool name or title.

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?

There is no output schema, so the description enumerates the returned metrics itself, and it covers the auth requirement and default time window. For a 3-parameter read tool this leaves no material gap an agent needs before calling it.

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%, so the description must compensate, and it does: slug is marked required, from/to are documented as ISO time strings, and the default range (last 30 days) is stated. That is meaning the bare schema does not carry.

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+resource (aggregate summary for a job over a time window) and enumerates the exact metrics returned: sessions, human turns, events, action calls, tokens, daily curve. This clearly separates it from siblings like get_job, list_sessions, and query_events.

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?

Gives an explicit trigger ('用户问这岗位最近怎么样/今天多少人来就用它') and an explicit anti-pattern ('不要靠聊天历史猜数字'). It does not name an alternative sibling tool for the case where raw session-level data is wanted, so it stops just 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.