tempo_submit_timesheet

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

Annotations already state destructiveHint=true, so the description doesn't need to repeat that. The description adds critical behavioral details: confirmation prompt behavior, the two-step fallback with confirmToken, and that the token must be from phase-1 and not invented. This goes beyond annotations and helps the agent understand the non-trivial side effects of invoking this tool. However, it doesn't describe what happens if the user confirms (e.g., irreversible submission) beyond the state change, which is partially covered by the description.

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 description is two sentences: the first states the core action and state transition; the second explains the confirmation mechanism. It is front-loaded with the main purpose and then procedural detail. No filler words, but the second sentence is somewhat long and could be split for readability. Overall, efficient and structured.

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?

Given the tool's complexity (confirmation flow, multiple modes), the description covers the essential behavioral aspects: confirmation prompt, MCP_CONFIRM_MODE, and the token-based fallback. It doesn't explicitly state the return format (but no output schema is present), and it assumes the agent understands the domain (e.g., 'OPEN' state). The description is sufficient for an agent to call it correctly, especially with schema covering parameter details.

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?

The schema descriptions cover 100% of parameters, explaining formats and defaults (e.g., 'to' defaults to period containing 'from', 'from' references tempo_get_periods). The description adds value primarily for confirmToken by explaining its purpose and usage constraints, which the schema already touches on ('ONLY for the two-step confirmation fallback...'). Since schema coverage is high, the description doesn't need to repeat parameter details; it does add some clarity on confirmToken's usage flow.

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 clearly states the specific action ('Submit a user's timesheet for the given period for approval'), the resource (timesheet), and the state transition (OPEN to WAITING_FOR_APPROVAL). This is distinct from sibling tools like tempo_approve_timesheet, tempo_reject_timesheet, and tempo_recall_timesheet, so an agent can differentiate it without ambiguity.

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 explains the confirmation flow, mentioning MCP_CONFIRM_MODE and the two-step fallback, which tells the agent when to use it. It doesn't explicitly list when not to use it compared to alternatives, but the state transition (from OPEN) implies submission is for timesheets not yet in approval, and the mention of reviewer account hints at the approval workflow. Minor gap: no direct reference to 'use tempo_approve_timesheet instead' for already-submitted timesheets.

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