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

Goes well beyond the annotations by disclosing the lock effect (no add/change/delete until rejected or withdrawn), that approval is permanent ('an approved week stays closed'), that owners are notified, and that the owner's plan must be Pro. It also explains the confirm-gated preview, so the agent knows what a non-confirm call returns.

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 action and its scope, then the side effects and preconditions. It is a dense run-on chain of clauses rather than structured sentences, but each clause carries operational information.

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 mutation tool with no output schema and rich annotations, the description covers the side effects, prerequisites, plan gating, notification behavior, and what the preview result contains. An agent has everything needed to invoke it safely.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning: 'week' accepts any day of a Monday–Sunday week, 'confirm: true' is required to act and otherwise returns a preview with hours per owner, and 'ownerId' is scoped to actual owners. These interpretations exceed the schema text.

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 ('Hands in the user's week of hours ... for approval') and scopes it precisely: submission goes to each project owner, or only to ownerId. This clearly distinguishes it from siblings like approve_timesheet, withdraw_timesheet, get_week_timesheet and list_timesheets.

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?

Gives concrete when/when-not conditions: a week can be submitted from its Monday on, a running timer must be stopped first, and a week already submitted or approved stays as it is. It doesn't explicitly name sibling tools to route to (e.g. for rejection or withdrawal), which keeps it from a 5.

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