aiworkhub_session_token_profile

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so 'READ-ONLY' mostly restates structured data. What the description does add is accounting semantics — that provider-reported tokens and prompt bytes are labelled separately — which matters for interpreting results. It says nothing about freshness/lag of observed tokens or limits, so the added value is modest.

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?

Two front-loaded sentences with no filler: mode, output composition, purpose, then the sibling alternative. The only redundancy is 'READ-ONLY', which duplicates readOnlyHint, but it costs almost nothing and reinforces safety at a glance.

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?

With an output schema covering the return shape and annotations covering the safety profile, the description only needs to convey purpose and output semantics — which it largely does. The residual gap is the session-vs-task framing against the single task_id parameter, which an agent may have to resolve by inspecting the schema.

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% and the single optional task_id is fully documented in the schema, so the description needn't re-explain it. However, it never clarifies how its 'session' framing maps onto that task_id scoping or what omitting it yields (the schema says 'every task'). Baseline 3 is appropriate when the schema does the work.

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 concrete analysis object — a session's input-token breakdown, split into observed provider tokens and separately-labelled prompt bytes — which is far more specific than the name alone. It also distinguishes itself from aiworkhub_task_cost_ledger. The only blur is that it talks about 'one session' while the sole parameter scopes by task, leaving the session/task relationship slightly ambiguous.

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 gives the use case ('see where one session's input tokens went') and names an alternative with the condition that selects it ('use aiworkhub_task_cost_ledger for per-task cost instead'). It does not mention other adjacent siblings such as aiworkhub_task_usage_report, so the routing map is not exhaustive, but the primary decision boundary is stated outright.

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