Get Research Proposal

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the "context" view drops the raw upstream record server-side (whose markdown would duplicate summary_markdown), and "full" exposes version history and signal counts with bodies in versions[].markdown. It stops short of describing error behavior for an invalid or unresolvable id/URL.

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 purpose sentence followed by a usage line and a tight bulleted breakdown of the enum. Every sentence earns its place; no restatement of the schema's enum list or boilerplate.

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?

An output schema exists, so return values needn't be documented, yet the description usefully clarifies the two response shapes and where proposal bodies live. Combined with the annotations and the idempotent read-only profile, an agent has everything needed to invoke this correctly.

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 the parameter burden. It fully explains the view enum — both values, the default, which is recommended, and the cost/benefit of each — but only implies the format of hypothesis_id_or_url through its name, without stating accepted ID vs URL forms.

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 verb (Fetch) and resource (a generated ML/AI research proposal) plus the source system, Lacuna. It also positions itself relative to sibling tools by naming search_lacuna with search_type="hypothesis" as the prerequisite step, so an agent can place it in the workflow without opening a schema.

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?

Explicitly states when to call it ('Use after search_lacuna(search_type="hypothesis")') and gives per-value guidance for the view parameter, including a when-not ('Use only when you need versions or signals' for "full"). This is the strongest form of routing guidance.

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