Read project

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

Annotations already cover the read-only/idempotent safety profile, but the description adds substantial behavioral context beyond them: 'no undo step,' the exact composition of the returned tree, the meaning of the four assignment arrays and the separate sharedAssignments[] case, the absent-field semantics, the sameRow display rule, the Builder.bReserve prerequisite that makes the call fail, and the warning that the 'critical' field is not a float indicator.

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?

The purpose and scope are front-loaded in the first sentence, and most sentences carry concrete information about the payload rather than filler. It is dense and long, with some overlap between the body text and the includePositionRange schema description, but nothing is gratuitous.

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 complex tree-read tool with one optional parameter, the description covers scope, payload structure, edge cases (sharedAssignments, empty arrays, absent fields), a failure prerequisite, and a semantic warning. An output schema exists, so return-value mechanics need not be restated, and the description still supplies enough framing to call the tool correctly.

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 the baseline is 3 and the schema already documents includePositionRange thoroughly. The description goes slightly beyond it by interpreting the result (total float of network analysis vs. free float, and that moving inside the range can drag successors along), which adds decision-relevant nuance even though much of the text overlaps the schema.

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 names a specific verb and resource ('read tasks and dependencies'), states the return shape ('the whole project as a tree'), and enumerates the payload (status date, subprojects, tasks with UUID/WBS/dates/flags/progress/effort, and every dependency). It also explicitly distinguishes itself from siblings by asserting 'There is no separate task list tool; this is the read path for them.'

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?

It clearly frames the tool as the read path for tasks and dependencies and rules out a competing task-list tool, which is strong routing guidance. However, it does not contrast against other read-oriented siblings such as analysis_report_get, resource_usage_list, or property_panel_get, nor state when a lighter read would be preferable.

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