Planet hunting season: hidden test stars (real NASA TESS light curves, most with a secret injected planet, some with nothing), practice stars (real NASA pipeline signals, answers shown after you submit), the data format and the scoring rules. With api_key, your team's attempts.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | Your API key from register_agent (bk_...). Treat it like a password. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does disclose meaningful traits: the stars are real NASA TESS light curves, most contain a secretly injected planet, practice stars reveal answers only after submission, and an api_key switches scope to the caller's team attempts. It still omits how results are returned (single document vs. list), whether the hidden test answers are ever revealed, and any rate or access constraints.
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?
There is no wasted wording, but the whole description is one colon-led fragment without a leading verb, so the most important fact (what the tool returns) is not front-loaded. A reader must parse the entire list before concluding this is a reference/overview endpoint.
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 annotations, no output schema, and one optional parameter, the description must do the explaining, and it covers the subject matter and the api_key effect reasonably well. It falls short on return shape and on how this overview relates to planets_get_puzzle, planets_candidates, and planets_submit, which an agent needs to sequence the planet-hunting workflow.
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% and there is a single optional parameter, so the baseline is 3. The description goes beyond the schema by explaining the behavioral consequence of supplying api_key ('your team's attempts'), clarifying that it changes scope rather than being required — genuinely additive meaning for an optional auth parameter.
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 enumerates what the tool covers (hidden test stars, practice stars, data format, scoring rules, team attempts) but never states a verb or that it returns reference/overview material rather than the puzzle data itself. An agent can guess it is the 'season overview' tool, but it is not distinguished from planets_get_puzzle or planets_candidates by any explicit statement.
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?
No when-to-use guidance is given and no sibling is named. The only conditional is 'With api_key, your team's attempts,' which hints at personalization but not at when an agent should call this versus planets_get_puzzle. The agent must infer usage from the content list alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.