Measure Answer Sizes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial context beyond them: it does not reduce query execution cost, it costs ~50 tokens instead of the full answer, it enforces a 16-query cap, it follows the active pool, and it refuses the same tools as batch for four named reasons. The only minor gap is that it doesn't detail per-item failure semantics beyond 'the refusal message names which one applies'.

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?

Dense and front-loaded – the core 'token count without the answer' claim and the decide-then-call usage rule come first, followed by mechanics. It is long, and the 'Max 16 queries per call' statement duplicates the schema description, but nearly every sentence carries information an agent needs.

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, yet the description fully specifies the return payload ({tool, ok, tokens, chars, returned, totalFound, truncated, budgetNote}) and explains the semantics of the ambiguous fields, including how budgetNote surfaces prose-level budget pruning. An agent has everything needed to call and interpret this tool.

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 the baseline is 3, but the description goes further: it clarifies that sessionId is shared once and must NOT be repeated inside each query's args, describes the {tool, args} item shape, and supplies a worked example with real args. That is meaningfully more than the schema provides.

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 precise verb+resource: it reports the exact token count of a read-only query's answer without returning it. It explicitly distinguishes itself from sibling batch ("Same shape as batch") and from the actual answering tools it prices, so an agent can route correctly without opening any schema.

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 concrete when-to-use conditions (decide whether a call is worth making, what budget to pass get_context/explain_symbol/pack_for_task, whether to narrow scope first) and an explicit when-not ("measure to DECIDE, then call once - do not measure every call by reflex"). It also explains what it refuses and why, which is strong alternative-routing guidance.

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