Leave requests

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

Annotations already mark the operation read-only and non-destructive, so the bar is lower. The description adds genuine behavioral context beyond that: visibility scoping of results, the overlap semantics for date-range filters, and a meaningful caveat that sick-leave free-text fields are never returned for data-protection reasons. These prepare the agent for response-shape gotchas. It is not exhaustive (no ordering or pagination behavior beyond the schema), hence 4 rather than 5.

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?

Two sentences with zero waste. The first front-loads the resource, scope, and filter capabilities; the second carries the data-protection caveat. Every clause earns its place and the description is easily scanned by an agent.

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?

With no output schema, the response structure is unspecified, but the description flags the one important ommission (sick-lave free-text fields) and covers the filter semantics and result scoping. The schema supplies page size, parameter formats, and the admin/supervisor/emplyee visability enforcement for user_id. Remaining gaps such as response ordering are minor for a filtered-list tool whose safety profile is already annotated.

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 coverage is 100%, so the baseline is 3. The description contributes 'overlap semantics' for date ranges, which adds meaning the schema's 'From/To date in YYYY-MM-DD format' descriptions lack. That is a single useful concept rather than substatial compensation, and the remaining parameter meanings are already fully carried by 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 identifies the resource (leave requests), enumerates its subtypes (vacation, flextime, sick leave), scopes it to the token owner's visibility, and lists the filter dimensions. The description reads as a noun phrase rather than an explicit 'Lists...', but the tool name supplies the verb and the content clearly distinguishes it from sibling list tools by resource. It stops short of a 5 because it never explicitly contrasts itself with a sibling like fortytimer_list_time_entries.

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?

Usage context is implied: the resource type and the visible sibling domains (balances, time entries, projects, users) make it reasonably clear this tool is for retrieving leave requests. However, there is no explicit when-to-use or when-not-to-use guidance, no alternative routing, and no statement about how this relates to the balance tools. The agent must infer the choice from the tool names.

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