whats_here

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

Annotations already cover read-only/idempotent/open-world safety, but the description adds real behavioral context beyond them: queries run 'all in parallel', partial failure is surfaced ('which sources failed'), and each hit comes with one-line evidence. That partial-failure disclosure is the key trait an agent needs to interpret a low-confidence verdict. It stops short of stating latency or rate-limit implications of the parallel fan-out.

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 decision-relevant question and the source list before the return-value detail; nearly every clause carries information. It is a single dense run-on sentence with stacked parentheticals, which makes the epoch and cutout clauses easy to skim past, but there is little true filler.

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 4-parameter aggregate query, the definition covers the input coordinate frame, the conditional asteroid path, the full verdict precedence order, and the failure-reporting behavior; an output schema exists so the return-shape notes are supplementary rather than load-bearing. An agent can decide to call it and interpret the result without opening the schema, with only radius_arcsec left unaddressed.

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?

With 0% schema coverage the description must carry everything: it specifies ra/dec are decimal degrees in ICRS, and gives the epoch format plus an ISO UTC example and its functional meaning (triggers SkyBoT asteroid lookup). The one clear gap is `radius_arcsec`, which is never mentioned, so its units and which sources honor it are left entirely implicit.

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 operation ('query TNS, SIMBAD, VSX, Gaia DR3, ExoFOP TOI/CTOI, ZTF (ALeRCE)' and SkyBoT) against a specific resource (a sky position), and enumerates the exact verdict taxonomy returned. This clearly distinguishes it from the single-catalog siblings (simbad, vsx, gaia, tns_object) as the aggregate cross-match tool.

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 framing question 'Is it already known?' plus the source list makes the intended use obvious: a first-pass identity check on a coordinate before deeper follow-up. The conditional 'if `epoch` is given' explains when asteroid matching activates. However, it never names a sibling or states when to prefer e.g. simbad/vsx for single-catalog detail over this fan-out call.

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