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

Adds substantial behavior beyond annotations: an uncached product_id REFUSES with a clear message rather than returning empty, weekly refresh cadence, data_as_of in every response, and the licensing terms permitting redistribution. Annotations cover the safety profile (readOnly/idempotent), and the description layers operational and failure-mode context on top.

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-loads the core value proposition and sibling routing in the opening sentence. Dense and largely waste-free, though the final licensing sentence is somewhat peripheral to invocation.

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 read tool with no output schema, it covers return contents (member labels, full history, data_as_of), coverage limits (curated high-demand ids only), and failure behavior. An agent has everything needed to call it correctly.

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 reinforces that omitting coordinate yields the whole table and that product_id alone checks coverage, but adds no syntax or format detail beyond what the schema descriptions already provide.

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 ('Whole StatCan table ... in ONE call, from a local Pipeworx copy') with scope and contents ('full history, every coordinate, member labels included'). Explicitly distinguishes itself from siblings statcan_cube_data and statcan_csv_url.

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 explicit when-to-use rules with named alternatives: use instead of statcan_cube_data when spanning more than one coordinate, and instead of statcan_csv_url when you need DATA not a download URL. Also explains the product_id-only coverage-check invocation.

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