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

With no annotations, the description carries the behavioral burden and does disclose key traits: practice stars are scored immediately, hidden stars are only compared against a secret answer, open-sky claims need snr >= 7.1, and team claims are pending vetting. It omits whether resubmission is allowed, what a wrong hidden-star claim costs, and what the call returns.

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?

Dense and front-loaded: the core action leads, then each mode is a compact clause. The telegraphic style (parenthetical field lists, missing articles) reads as slightly cryptic but wastes no words.

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 complex multi-mode submission tool with no annotations and no output schema, the description covers inputs well but leaves the response side entirely implicit — an agent cannot tell whether it receives a score, a validation error, or a pending status per mode. Adding even one sentence on what comes back would close the main 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 only 18% across 11 parameters, so the description must compensate and largely does: it assigns meanings to puzzle_id, verdict, period_days, depth_ppm, duration_hours, tic_id, sector and snr. Its most valuable contribution is distinguishing t0 units — days from start for puzzle claims versus BTJD for open sky — a distinction an agent would otherwise get wrong. Only notes and api_key go unaddressed, and their schema descriptions cover them.

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 first sentence gives a specific verb ("Propose a claim") and the rest enumerates the three submission modes (hidden star, practice star, open sky), so an agent knows exactly what this tool accepts. It does not fully separate itself from siblings like planets_candidates or submit_result, but it does name planets_vet as the downstream gatekeeper.

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?

Usage is spelled out by mode: use puzzle_id + verdict for hidden/practice stars, omit puzzle_id and supply tic_id/sector for open sky, and expect team claims to stall until a DIFFERENT teammate calls planets_vet. That is clear conditional guidance, though it never says when to prefer another sibling such as planets_candidates.

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