start_project_request

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

Goes well beyond the annotations by disclosing a real side effect (starting a new round invalidates the prior plan approval), a conditional-parameter rule tied to project workflow_selection, and two post-call obligations: acting immediately on a non-null action_required rather than ending the turn, and prefixing the user reply verbatim with meeting_mode_notice.text. These are exactly the non-obvious behavioral traits an agent cannot derive from readOnlyHint=false / destructiveHint=false.

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-loads the core action, then the scoping rule, then the prohibitions, then the result-handling rules — a sensible ordering where each sentence carries distinct information. It is dense and the irregular indentation/line wrapping makes it slightly harder to scan than a clean bulleted structure would.

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?

An output schema exists, so return-value shapes need not be explained, and the description nonetheless covers the two result fields that require caller action (action_required, meeting_mode_notice). Combined with the workflow-selection rule and the turn-continuation contract, an agent has everything needed to invoke and follow up 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 schema already documents all five parameters including the workflow_selection='pm' condition, which the description largely restates. The only added meaning is the instruction to call list_workflows before passing `workflow`; acceptance, project_id, requirement, and wait_seconds receive no extra description-level semantics.

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 and resource ('Begin a NEW authorized project change, dispatch the workflow's first step') and immediately bounds scope with 'NEW', separating it from continuation/inspection operations. An agent can distinguish this from siblings like advance_project, resume_pending_dispatch, or get_task_status 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?

Explicitly states the negative case: never use it to continue, retry, recover, or inspect an existing task, and explains the consequence (starts a new round, invalidates prior plan approval). It also gives a prerequisite (call list_workflows first) and the condition under which `workflow` matters. The one gap is that it never names the specific sibling tools an agent should use instead for continue/retry/inspect, leaving that mapping to inference.

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