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

Annotations already declare readOnly/idempotent/non-destructive, so the description only needs to add behavior beyond that. It does: it discloses the return shape (time buckets, per-signal split) and the intended pipeline into generate_chart, which helps an agent plan a multi-step call. It doesn't discuss default date range behavior when since/until are null, a minor gap.

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 tight clauses, zero filler: purpose first, then the usage/chaining instruction. Every phrase earns its place and the most decision-relevant information is front-loaded.

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 present, the description needn't explain return values, and annotations cover the safety profile; the description supplies purpose, usage context, and chaining. The only omission is what a null since/until implies, a small but real gap for a time-series 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 80% and the schema itself documents since/until as ISO bounds, granularity's 'week' default, and the includeLowQuality exclusion rule — so the schema carries the semantic load. The description only echoes 'bucketed by day or week' (the granularity parameter) and adds nothing about projectId or the null date semantics, so baseline 3 is correct.

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?

Names a specific verb+resource: 'Response volume over time for a project,' plus the dimensions of the output (bucketed by day/week, split by positive/negative/neutral signal). This clearly separates it from aggregate siblings like project_stats or question_breakdown, though it never names those alternatives explicitly.

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 states when to reach for it ('trend / volume-over-time questions') and gives a concrete downstream step ('feed the points into generate_chart (line)'), which is genuinely actionable routing. It lacks an explicit 'do not use for X' exclusion against the other stats siblings, so it stops 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.