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

Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds valuable operational context: 'SDMX v3.0 API — ADB open data, no auth, 20 req/min' and the return structure ('structured observations with values, units, data sources, and footnotes'). It also discloses defaults, annual-frequency-only constraint, and data availability, going well beyond the annotations. No contradiction exists.

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?

The description is dense but front-loaded with the primary action, followed by coverage, workflow, example, and source/rate-limit info; every sentence carries useful information. It is a bit long, but the complexity of the API justifies it; a 4 is appropriate because it could be slightly better structured for scannability.

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?

The description covers coverage, workflow, example, rate limit, auth, defaults, and response contents, so an agent has nearly everything needed to invoke it correctly. Since an output schema exists, detailed return-value documentation is unnecessary. The only notable gap is the mismatch between the workflow tool names referenced in the description/schema and the actual sibling tool names, which could cause an agent to attempt non-existent tools.

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?

The schema already describes every parameter with ranges, defaults, and examples, so the baseline is 3. The description adds a complete worked example (dataflow=EO_NA, indicator_codes=[NGDP_XDC], economy_codes=[PRC,IND], start_year=2015) and clarifies data availability ('most series begin 1990–2000'), which helps an agent pick valid values. The main drawback is that the parameter-level suggestions reference non-matching discovery tool names, slightly undermining reliability.

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?

The description opens with a specific verb and resource: 'Fetch annual macroeconomic time-series data from the ADB Key Indicators Database for any combination of Asian Development Bank member economies and SDMX indicators.' It clearly distinguishes itself from the exploration siblings by positioning itself as the data-fetching step and gives concrete topic coverage and example codes. The only minor weakness is that the internal workflow references use names like 'adbkidb.dataflows_list' while actual siblings are 'adbkidb.explore.*', but this does not obscure the tool's core purpose.

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?

The description provides an explicit three-step workflow: list dataflows, find indicator codes, then use this tool to fetch values, and also points to adbkidb.economies for economy codes. It clarifies decision-relevant defaults such as start_year defaulting to 2000 and end_year to the current year. However, the referenced discovery tool names do not match the actual sibling names in the environment (e.g., 'adbkidb.dataflows_list' vs 'adbkidb.explore.dataflows'), which could mislead an agent trying to follow the workflow.

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