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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantive behavior beyond them: the full return payload (task dates and float, critical path, milestones, end date, interactive Gantt, CSV/.ics/SVG downloads) and error handling ("Detects dependency loops and unknown task names"). It also scopes the calculation model (business-day calendar with country holidays vs. calendar days), which determines output correctness.

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?

Front-loaded with the triggering conditions before the mechanics, and every sentence carries content (inputs, outputs, limits, exclusions). The single dense block runs long, but there is little true filler; a sentence break between behavior and exclusions would improve scanability slightly.

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?

For a high-complexity scheduling tool with 8 parameters and nested task objects, the description covers inputs, computation model, outputs, downloads, and boundaries. With an output schema present it need not explain return values further, yet it still names the deliverables, leaving nothing an agent needs missing.

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%, so all eight parameters are already documented at field level. The description echoes their grouping (durations in days or weeks, finish-to-start dependencies with optional lags, start-no-earlier-than, owners, milestones, calendar mode) but adds no syntax or format detail beyond what the schema states. Baseline 3 applies since the schema does the heavy lifting.

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?

The description opens with a specific verb and resource ("plan project timeline" via Gantt chart / milestones / CPM) and enumerates the exact computations performed: ES/EF/LS/LF, total float, free float, critical path. An agent can immediately tell this is a CPM scheduling engine rather than a generic date utility.

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?

Strong triggering conditions ("the user wants a Gantt chart... or asks for early start, early finish...") plus explicit exclusions ("Does not save projects, sync with project tools, track progress, or level resources" and "Do not use for a single date difference or for daily to-do planning"). The one gap is that the sibling compare_timeline_scenarios is never named, so the agent gets no routing signal for scenario comparison.

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