find_sources

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

With no annotations, the description carries the behavioral burden. It discloses that the tool is 'Free and keyless', that busy services are reported as 'skipped', and that results are recent and enriched with affiliations and PDF links. This goes beyond the bare schema, though the exact return structure and broader failure modes remain implied.

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 three tight sentences that front-load the main purpose and then add operational details about kinds, free/keyless access, skipped services, and the next workflow step. It is slightly dense but contains no wasted sentences.

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 simple three-parameter tool with no annotations and no output schema, the description covers the essential selection and invocation context: result substance, defaults, auth requirements, busy-service behavior, and the subsequent fetch/cut workflow. The main remaining gap is the 'limit' parameter.

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. It does define 'kinds' and its default ('papers', 'news' default both), but it gives no explicit semantics for 'query' or 'limit'. The query's meaning is inferable from the tool's purpose, but 'limit' is left undocumented.

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?

Description states a specific verb and resource: 'Find NEW evidence to cut: recent scholarly papers (with author affiliations for quals and free PDF links) and current news articles.' It also references the downstream workflow with fetch_source, which helps distinguish it from search-oriented siblings, though it does not explicitly contrast with search_cards or caselist_search.

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?

It gives clear context for when to use the tool: as the first step in finding new evidence to cut, followed by 'fetch_source a result's url and cut it.' It also explains the behavior of the 'kinds' parameter and the 'skipped' case. However, it stops short of explicitly stating when not to use it or naming alternative tools.

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