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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing a server-side behavior—the raw upstream record is dropped in the 'context' view because its markdown duplicates summary_markdown—and where proposal bodies live in 'full' (versions[].markdown). This is substantive disclosure beyond structured fields.

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 followed by a clean bulleted breakdown of view modes; every sentence carries information. The parenthetical about duplicated markdown is slightly dense but justified since it explains the field dropping.

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 an output schema present, return values need not be re-explained, yet the description still clarifies response shapes and where bodies live. For a two-parameter read tool with full annotation coverage, nothing an agent needs to call it correctly is missing.

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 load; it fully explains both enum values of 'view' with the default and a recommendation. It does not explain the accepted format of hypothesis_id_or_url beyond its name, leaving a small gap.

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 and resource ('Fetch a generated novel ML/AI research proposal') and names the source (Lacuna), which separates it from sibling retrievers like get_paper or get_direction. An agent can tell what it returns without opening the 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 names the prerequisite call (search_lacuna with search_type="hypothesis") and gives a when/when-not rule for the view parameter: 'full' only when versions or signals are needed, otherwise context is 'default, recommended'.

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