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

Discloses semantics that no annotation or structured field carries: a `hidden: true` flag exists, hidden centers still hold bookings and still count toward company-wide figures, but are no longer selectable. This is exactly the kind of data-interpretation context an agent cannot derive from readOnlyHint/openWorldHint alone.

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?

Well front-loaded: purpose first, then usage, then the hidden-flag caveat. Mostly taut-free, though the internal reference '(Issue #89)' is noise for an agent and the instruction 'say that they are hidden' veers into output formatting rather than tool behavior.

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 parameters and no output schema, the description carries the full burden and meets it: it names the returned fields (IDs, names, hidden flag) and explains how to interpret and order them. Nothing an agent needs to call and use this tool correctly is missing.

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 there is no parameter semantics to add and the baseline applies. The description instead spends its words on output-row semantics, which is appropriate for a no-arg listing tool.

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+resource ('Get list of all cost centers') and immediately clarifies the payload ('with their IDs and names'), plus the question type it answers. That clearly separates it from sibling tools like search_cost_center_transactions or aggregate_pnl_by_cost_center, which operate on transactional/aggregate data rather than the master list.

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?

Explicitly says to use it 'to answer questions about what cost centers exist', which gives the agent a clear trigger. It also defines how to present hidden entries, but it never names an alternative tool or states when NOT to use this one (e.g. when the agent actually needs bookings per cost center).

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