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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds real operational context the annotations cannot: deterministic validation, no authentication required, the exact failure output shape ('valid=true or one error per failing JSON path'), and a telemetry notice with an opt-out env var. It stops short of documenting any size/time limits on large portfolios.

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?

Dense but well ordered: what it does, when to call it, what it does not do, tolerated input shapes, sibling routing, then return/telemetry details. It is long for a single-parameter validator, but nearly every sentence carries a distinct fact, with only minor overlap between the description body and the schema prose.

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, yet the description still tells the agent the shape of success and failure results (valid=true vs. one error per failing JSON path), which is exactly what a validation tool's caller needs to branch on. Combined with the enum/range scope statement and the telemetry disclosure, nothing material 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?

Schema description coverage is 100% and there is only one parameter, so the schema carries the shape documentation; the baseline is 3. The description does add outcome-relevant semantics beyond raw shape by stating that both pillar encodings ('bare numbers or { value, confidence } objects') are accepted, which tells the caller what will and won't fail validation rather than just what the field looks like.

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 (validate a BVF v1.0 portfolio document) and immediately scopes it: 'it checks required fields, taxonomy values and 0–100 pillar ranges only; it does not judge the evidence or calculate a verdict.' That negative scoping cleanly separates it from score_portfolio and score_initiative.

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 document came from a file, another system or hand-built JSON and its structure is uncertain') plus named alternatives with their selecting conditions: assemble_portfolio for in-conversation lists, score_portfolio when ready for verdicts, sequence_portfolio only after scoreable. Nothing is left to inference.

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