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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds genuinely new traits: the computation is deterministic, it returns intermediate steps the caller is expected to cite, and it may emit warnings that must be surfaced. It does not say what triggers warnings or how invalid inputs (e.g. abated months beyond the term) are handled.

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, front-loaded with what is computed and in what units, then the usage directive and citation requirement. No filler or restatement of the title.

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 a nested-but-fully-documented input schema and no output schema, the description carries the return-value burden and does name the key returns (the three rent figures, steps, warnings), but never sketches the response structure beyond that. For a deterministic calculator this is nearly sufficient, though a note on partial-failure or warning cases would close the 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; the description still adds the grouping of ti_allowance_psf, leasing_commissions, and other_concessions as landlord concessions applied against rent, and frames discount_rate_annual as selecting the discounted versus straight-line output. The remaining parameters (schedule internals, include_monthly, round_rate_to_cents) are left entirely to 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?

States a specific verb (compute) and resource (net effective rent) with three named variants and explicit output units ($/SF/yr), plus the concession categories netted out. The mention of free rent, TI, commissions, and discounting clearly separates it from calc_rent_schedule, which only builds the base-rent stream.

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?

"Deterministic: use this instead of doing the math yourself" is a clear call-to-action with a citation obligation (calc.net_effective_rent@1) and an instruction to surface warnings. It stops short of stating exclusions, e.g. when to use calc_rent_schedule first or when calc_compare_proposals supersedes this for multi-scenario work.

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