constellation_raw

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

With no annotations, the description carries the burden of behavioral disclosure. It discloses that the response is raw/unprojected, very large (~330 KB for a single chain), and contains data mostly belonging to other studies. This gives the agent important expectations about size and content. It does not explicitly state that the operation is read-only, but the 'response/debugging/investigating' framing strongly implies a non-mutating fetch.

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 compact and front-loaded. The first sentence states exactly what the tool returns, the second gives the use case, and the third provides the alternative plus a size warning and a tuning hint. Every sentence earns its place and there is no redundant wording.

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 the tool's purpose, use case, size, and one parameter behavior, but it omits the meaning of `uri` and `max_nodes`, which are essential for calling the tool correctly. There is no output schema, so the description should provide more return-shape detail; it does describe 'every node and edge,' but the parameter gaps prevent full contextual completeness.

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 compensate by explaining the parameters. It only explains `depth` ('Lower `depth` to shrink the walk') and gives no guidance on `uri` or `max_nodes`. The agent is left to guess what `uri` should reference and what `max_nodes` controls. This is a significant gap for a tool with three parameters and no schema-level descriptions.

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 clearly identifies what the tool returns: 'The unprojected /np/constellation response, including every node and edge.' It uses a specific resource and distinguishes itself from the sibling `constellation` tool by calling this the raw/debugging variant. An agent can immediately tell what this tool does and how it differs from the normal `constellation` endpoint.

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 explicitly states when to use this tool: 'For debugging the graph itself or investigating an upstream data problem.' It also names the preferred alternative: 'Prefer `constellation` for normal use.' It even provides a practical tuning hint—'Lower `depth` to shrink the walk'—which gives actionable guidance for invocation.

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