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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds genuinely non-redundant behavior: deterministic calculation, no authentication required, anonymous telemetry with an explicit opt-out env var (AIBVF_TELEMETRY_DISABLE=1), and the shape of the result (low/high EUR range, drag rate, pace-gap severity, drivers, source). It also discloses the caveat that industry is accepted but does not affect the result yet.

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?

Front-loaded with purpose, then triggers, exclusions, parameter mechanics, return shape and operational notes in that order. It is dense rather than padded, though the parameter-mechanics sentence overlaps somewhat with the already-detailed schema descriptions.

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 deterministic read-only calculator with an output schema, the description covers everything an agent needs: when to call it, when not to, what drives the result, what industry does (nothing yet), what comes back, and the auth/telemetry profile. No material gap remains.

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% and the enum descriptions are already rich, so the baseline is 3. The description adds value by stating how parameters interact ('ai_tier and readiness together set the drag rate and pace_gap', 'revenue_eur sets the absolute EUR range') and by flagging that industry is interface-only and does not change the calculation — a meaningful caveat an agent would otherwise mis-assume.

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: quantifying the annual EUR cost of an AI ambition outrunning the operating model (organisational drag / cost of waiting). It also scopes itself against siblings by naming score_initiative, diagnose_process and recommend_improvements as the tools for adjacent questions, so an agent can route without opening another schema.

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?

Explicit trigger ('CALL THIS when the user needs the cost of waiting... or when a Fix plan needs a cost-of-waiting figure') followed by explicit exclusions mapped to named alternatives ('Do not use it to score an AI initiative... use score_initiative for the investment verdict, diagnose_process for a running process, recommend_improvements for the change plan'). This is textbook when/when-not/alternative guidance.

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