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

With no annotations the description carries the full burden and does most of it: it discloses cost ("Free · 10 credits"), defines link_confidence values ('verified' vs 'unverified'), and warns that a linked repo is not proof the code runs. It also sketches the returned fields and the scope.interpreted_as behavior. Minor gap: no statement about behavior when no lane or repo matches, or about result ordering beyond "best first".

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 with the core promise ("State of the art you can actually RUN") followed by the return shape, then usage, then the sibling contrast and caveat, then cost. Dense but every sentence contributes; the only slight drag is the long parenthetical enumerating repo fields.

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 7-parameter tool with no output schema and no annotations, the description covers purpose, return contents, the confidence caveat, and cost — enough to call it correctly. It stops short of describing pagination or empty-result behavior, which is the only material omission.

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 100%, so the schema already documents all seven parameters, including the topic-vs-dataset-vs-query fallback logic and per_lane/limit semantics. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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+resource+scope: per benchmark lane, the best-ranked paper that ships a code repo, plus repo metadata, rank, and accuracy gap versus the leader. It explicitly distinguishes itself from sota_papers ("two thirds of papers with benchmark numbers ship no code, so this answers a different question"), so an agent can route correctly without opening either 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?

Names concrete triggering questions ("best method with code for X", "what can I reproduce today", "picking a baseline to build on") and names the alternative tool plus the condition that selects it. The code-vs-no-code split gives an implicit when-not rule, which is exactly what routing needs.

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