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

Annotations declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds valuable behavior beyond that: determinism, that it returns balance due plus a full trace, and that warnings should be surfaced. It does not detail rate limits or failure modes, keeping it below a 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?

The description is two dense sentences: the first front-loads the full scope of the reconciliation, the second delivers the key operational instruction. Every clause maps to a real behavior or parameter family, with no filler.

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 complex 7-parameter nested tool with no output schema, it covers the calculation domains, tells the agent not to reimplement the math, and notes a trace plus warnings are returned. It omits the currency/units and what the trace contains in detail, but the schema already documents units, leaving only a minor gap.

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, but the description adds meaning by naming the cap methods (compounding_from_base, simple_from_base, year_over_year) and the structural choices (base year or expense stop) in prose. It explains the conceptual inputs rather than restating field syntax, though it does not clarify every parameter.

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 states a specific verb and resource ("Reconcile a tenant's annual CAM charge") and enumerates the exact lease mechanics handled: exclusions, occupancy gross-up, pro rata share, controllable caps, base year or expense stop, and estimates paid. It clearly distinguishes this from siblings like calc_net_effective_rent or calc_rent_schedule, which do not perform CAM reconciliation.

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 explicitly says "use this instead of doing the math yourself" and instructs the agent to cite formula calc.cam_reconciliation@1 and the returned steps, surfacing warnings. This is direct when-to-use guidance with a clear alternative (manual math) ruled out, though no sibling tool is named as an alternative.

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