radio_sources_now

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

With no annotations, the description carries the full burden. It does disclose useful behavior: no auth needed, the default observer site is TART's own NZ location (-45.87, 170.60, 100 m), and limit is capped at 50. It does not say what the response contains (source names, coordinates, elevation values?) or whether results are computed live, which are the remaining behavioral gaps.

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 one-line purpose and auth note, then examples, then a compact Args block. The examples are slightly redundant with the opening sentence but earn their place by showing natural-language trigger phrasings. No filler beyond that.

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 five-parameter, no-annotation, no-output-schema tool, the description covers input semantics well but says nothing about the return shape — an agent cannot tell whether it gets a list of source names, RA/Dec, or altitude/azimuth, nor how large the payload is. That gap matters precisely because there is no output schema to fall back on.

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 0%, so the description must carry all parameter meaning, and it does: lat/lon with their NZ fallbacks, alt in metres, elevation as minimum degrees above horizon with an explanation that higher values exclude low-sky targets, and limit with default 15 and max 50. The only shortfall is that the 50-cap is stated without saying what happens if exceeded (clamp vs. error).

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?

Names a specific verb and resource: returns radio sources currently observable by the TART open radio telescope, and adds a concrete scope (observer location, minimum elevation). The two example queries ('what's overhead now?', 'which satellites is the Dunedin telescope seeing') make the intent unambiguous. It does not distinguish itself from nearby siblings such as alma_search or cadc_observations, which keeps it at 4.

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 example queries imply the usage context (real-time visibility from a ground site), and 'no authentication required' removes a prerequisite question. However, there is no explicit when-not guidance and no naming of an alternative tool when the agent wants catalog lookups or archival radio data rather than live visibility.

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