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

Annotations already declare this a safe, idempotent read, so the description only needs to add gating context — and it does, disclosing that a developer key is required and that free evaluation silently resolves to a fixed training-set sample rather than true point-in-time data. That sample-substitution caveat is behavior an agent could not infer from the schema and materially affects result interpretation. It does not describe response shape, but no output schema exists to cover that gap either.

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 short sentences, front-loaded with the core identity of the tool, then use case, then entitlement constraints. No sentence is redundant and nothing is buried.

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 an 8-parameter read tool with full schema coverage and rich annotations, the description covers purpose, use case, and access gating. The remaining gap is that a caller does not know what a 'board' row contains or how the snapshot relates to the live board, which matters for a point-in-time tool with no output schema.

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%, so the schema already documents as_of format, limit bounds, cursor opacity, league codes, and tier values. The description only restates the as_of format (ISO 8601 with time zone) and adds no meaning to the filtering parameters like stat, search, or tier. Baseline 3 is appropriate.

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 action and resource: retrieve the board as it stood at a past instant, parameterized by as_of. The temporal qualifier distinguishes it from the current-state siblings like get_projections and get_demo_projections, though the term 'board' itself is never defined and no sibling is named explicitly.

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?

Gives clear use cases ('For backtests and point-in-time questions') and a routing rule for the free tier ('Free evaluation uses the fixed training-set sample'), which points the agent to get_training_set instead. It does not spell out the inverse case (use get_projections for the live board), so the alternative is implied rather than named.

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