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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds the genuinely non-obvious behavior: it returns screen/button/field instructions and "opens nothing by itself," which explains why a readOnly tool exists for a reject action. The sparse API note adds a little environment context but no rate limits or error behavior.

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 the crucial "returns instructions, opens nothing" caveat, all in a compact block. The trailing API availability sentence (with a check date) is tangential to invoking the tool and is the one part that doesn't fully earn its place.

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 zero-parameter, no-output-schema tool, the description covers what it returns and the required next step via the browser tools. The missing piece is how the specific absence request is identified, which matters given the absence of any input fields.

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 input schema is empty, so there are no parameter semantics to document; baseline 4 applies. The description's silence on how the target request is conveyed is a contextual gap rather than a parameter-documentation failure.

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 ("Reject absence request in the user's own Bizneo account") and immediately clarifies the tool's actual output: a step-by-step guide, not the performed action. Sibling differentiation (approve vs. request absence) is carried by the name rather than the prose, which keeps it just short of a 5.

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 clear follow-through guidance: call this first, then execute with cotlet_browser_* tools. However, it never addresses selection or prerequisites — with zero parameters, an agent has no stated way to identify which absence request to reject (e.g., listing requests first), and no sibling alternative is named.

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