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

Annotations already cover readOnly/non-destructive/closed-world safety, but the description adds substantive behavioral context: output is redacted by role, with money fields hidden from non-owners. That access-dependent disclosure goes beyond structured data. It stops short of pagination, caching, 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?

Two tight sentences, front-loaded with the summarized fields and ending on the permission distinction. The budget thresholds (ok, warning from 80%, over) are embedded without padding, and no sentence is wasted.

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 no output schema, the description must carry the return-value burden, and it does so well by enumerating the metrics and the role-based view differences. The remaining gap is that it never ties the boardId input to the project concept.

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% and the single parameter boardId has no description. The description says 'project' but never clarifies that boardId identifies the project being summarized, so it fails to compensate for the schema gap on the only input the agent must supply.

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 ('Summarizes') and resource ('a project') and enumerates the exact content returned: tracked time, billable time, billable amount, budget usage, per-person hours. An agent can distinguish it from generic project readers like get_board or get_project_settings.

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?

The description conveys the role-dependent context (owner sees everything, other members see totals plus own hours) but never states when to choose this over siblings such as get_billing_report, get_workload, or get_time_report. Usage is implied rather than routed, leaving the agent to infer selection.

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