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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: the default-null behavior triggers a shipped synthetic example, and rights_confirmed is a licensing gate that explicitly 'does not verify a licence'. That caveat is useful, but the description says nothing about error behavior for malformed desk data, how the multiplier is derived, or what happens when rights_confirmed=false with a supplied request.

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?

Three tight sentences with the output scope front-loaded and the two operational rules following. Nothing is redundant. The opening clause is telegraphic (a bare list of outputs without a verb), which costs a little immediate clarity but is defensible for a domain-savvy agent.

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?

An output schema exists, so return values need not be explained, and the licensing/synthetic behavior is covered. What is missing for a tool requiring a sixteen-field nested request is any orientation on the data_mode enum versus rights_confirmed interaction, or the units/conventions of the capital inputs. Adequate to invoke, thin for invoking correctly with real data.

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 description coverage is 0%, and the nested ImaCapitalRequest carries roughly sixteen required fields (imcc_latest, ses_average_60d, drc_average_12w, sa_green_amber, desks[].pla_zone, etc.) that the description never touches. It does explain the two top-level parameters well — request omitted means synthetic, rights_confirmed is the permission flag — but the bulk of the required input surface is left entirely to the schema titles.

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 names a specific computation and its outputs: 'FRTB IMA aggregate capital, multiplier, amber-desk surcharge and RWA', anchored by regulatory references (MAR33, MAR32.9). An agent can tell this is the IMA capital aggregation tool. It does not, however, explicitly distinguish itself from related siblings such as risk_frtb_imcc or risk_frtb_pla, which an agent might otherwise consider.

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?

'Omit the request to run the shipped synthetic example instead' gives a concrete when-to-do-what for the null path, and 'For supplied data, require permission and set rights_confirmed=true' gives the precondition for the real path. This is clear conditional guidance. It stops short of naming alternatives (e.g. the IMCC or PLA tools) or stating when this aggregate is the wrong choice.

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