retrieve_evidence

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

With no annotations, the description carries the full behavioral burden. It discloses one important limitation ('Results are not complete paper summaries') and the odd framing that 'The main LLM writes the answer,' but says nothing about permissions, rate limits, result ordering, or what the citations look like in the response. Partial disclosure only.

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?

Four short lines, front-loaded with purpose then scoping then a usage hint then a limitation. No filler, though the 'The main LLM writes the answer' line is a slightly awkward aside that doesn't directly help invocation.

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?

No output schema, no annotations, and 3 parameters at 0% description coverage mean the description must do more. It covers purpose, scoping, and one limitation, but omits top_k behavior, result count expectations, and any failure modes, leaving real gaps for an agent invoking it blind.

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 explain paper_ids semantics (scoping to chosen papers vs. current local index) and implies question is the search query and that multiple focused subqueries are expected, but top_k is left entirely unexplained with no default rationale. Partial compensation for a 0% coverage schema.

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 opening sentence names a specific verb (retrieve), resource (original scientific passages), the retrieval mechanism (semantic + keyword search), and the return enrichment (DOI citations). This clearly distinguishes it from read_summary or read_passage, though it does not explicitly name the sibling it replaces the way a 5 would.

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 states scoping behavior for paper_ids ('omitted IDs search the current local index'), advises focused subqueries for multi-aspect questions, and routes the agent to read_passage for context. This is clear context-setting, but no explicit when-not-to-use conditions (e.g., vs search_papers) beyond that single routing hint.

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