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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered; the description adds the useful behavioral detail that output is a dimension→code+label map and that codelists can be very large. It does not mention response shape beyond that or any latency/size caveats outside the max_codes_per_dimension param, leaving a modest gap.

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 core purpose, then usage, then scope, then examples — a sound ordering with no filler sentences. The registry enumeration duplicates the schema enum, which is minor redundancy but serves scannability in the description itself.

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?

With no output schema, the description carries the return-value burden and does so ('ordered dimensions and, for each, the valid codes with labels'), which is the essential thing an agent needs. It stops short of describing the exact response envelope or how truncation appears when max_codes_per_dimension caps results, leaving a small but real gap.

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, but the description adds real usage value with concrete per-registry examples ('une_rt_m' for eurostat, 'WS_CBPOL' for bis) that demonstrate id casing and typical identifiers. It does not explain the agency/version override semantics in the description, but those are already documented in the schema.

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 — 'Get the structure of one dataflow from any SDMX 2.1 registry' — then specifies exactly what is returned: ordered dimensions plus valid codes with labels. It distinguishes itself from the sibling sdmx_find_dataflow (discovery) and sdmx_codelist (standalone code lists) by framing its output as the key/dimension map for one dataflow.

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 an explicit sequencing instruction ('use it before calling a registry-specific get_data tool') and names the alternative for specific cases ('For ILO or ABS dataflows, prefer the ilostat/abs-au packs' own dataflow_structure tool'). It also enumerates the eight registries it does cover, so the agent knows when this tool applies versus when it does not.

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