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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious context beyond that: the tool opens nothing, returns procedural steps rather than data, and requires a Cloud Browser session for the actual work. The only blemish is the tension between the "List shifts" opening and "opens nothing by itself."

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 most important behavioral fact (this returns instructions, not data) is buried mid-sentence behind a misleading lead. The trailing note "Deputy's official API: Yes, Deputy has a full REST API, but no official MCP server (checked 20 Oct 2026)" is marketing/meta commentary that does not help an agent decide or invoke, and the chatbot-name enumeration adds no decision value.

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 guide tool with no output schema, it does explain what comes back (step-by-step screens, buttons, fields) and what to do next. What it leaves unresolved is whether any actual shift data is surfaced and what the guide's format looks like, so an agent cannot be fully certain of the return shape.

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 tool takes zero parameters, so the baseline is 4, but the schema coverage is technically 100% of an empty object. The description does not explain that the absence of parameters is intentional (no account, date range, or employee filter is accepted), which is a meaningful omission for a tool whose name implies filtered listing.

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 does eventually state the real behavior ("returns how to do it in Deputy step by step (screens, buttons, fields) and opens nothing by itself"), but the opening clause "List shifts in the user's own Deputy account" reads like a data-fetch, directly at odds with the guide-only function revealed one clause later. An agent skimming name plus first sentence could expect shift records. The actual purpose is only clear after reading the whole thing.

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?

It gives a clear follow-up path ("then do it with the cotlet_browser_* tools in the user's Deputy Cloud Browser"), which is useful routing. But it never says when to choose this over siblings like deputy_list_employees, cotlet_app_guide, or when a direct data answer is needed, and it offers no when-not conditions.

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