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

Goes well beyond the annotations: metering (one plan credit per scored call), that absent boards are not charged, that large boards are scored from a capped sample with a 'truncated' flag to relay, and that it reads real Pinterest Pins rather than only Tailwind-scheduled ones. These are cost, fidelity, and failure-mode details an agent cannot get from readOnlyHint/openWorldHint alone, and none of them contradict those hints.

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 the 'Use this when' trigger, then each subsequent sentence carries a distinct operational rule (source of Pins, metering, absent handling, truncation, account ambiguity) with no restatement of the name or schema. Dense but every sentence earns its place.

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 shape needn't be explained, and the description covers the remaining agent-relevant gaps: cost per call, degraded/absent results, sampling truncation, and multi-account disambiguation. Nothing needed to call this correctly or interpret its output 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 coverage is 100%, so the baseline is 3; the description earns a bump by adding account-selection semantics for accountId (don't pick an account on the user's behalf when multiple exist), which is a constraint the schema does not express. It says nothing extra about boardId or keyword, but those are already fully documented.

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 and resource — scores a board's live Pinterest content against a keyword and returns the Pins with per-Pin relevance — which is distinct from siblings like list_board_pins (raw listing) or get_pin_analytics. The opening clause names the exact user question it answers, so an agent can route to it without inspecting the 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 ('user asks how well a board covers a keyword or topic', 'auditing whether a board is on-topic'), explicit anti-pattern ('score the board once and reuse the result rather than re-calling per question'), and explicit precondition (ask which account if list_accounts returns more than one). It also tells the agent what to do with an 'absent' result — report unknown coverage, never poor coverage.

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