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

Annotations already declare readOnly, openWorld, and non-destructive, so the safety profile is covered. The description adds real value beyond that: per-DOI status states (ready, collecting, settled empty), stance counts, and the distinction between Cerebrum's stance label and Semantic Scholar's purpose label. It omits auth, rate limits, and pagination, but the core behavioral contract is disclosed well.

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 first sentence front-loads the purpose, and the following sentences deliver status, counts, and label semantics without padding. Each sentence carries information, though the description is dense and would benefit from separating the status semantics from the sentence-structure detail.

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 two-parameter read tool with an output schema, this is close to complete: it explains the response shape, the meaning of the 'collecting' state, and the dual-labeling of sentences. The one gap is that the schema marks zero required parameters, yet the description never states that at least one of doi or dois must be supplied.

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 doi/dois parameters and their mutual exclusivity are fully documented in the schema. The description's 'for each DOI' hints that multiple DOIs are supported, but adds nothing about the 20-item cap or the optional-both nature of the parameters. Baseline 3 is appropriate when the schema does the heavy lifting.

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 description names a specific verb and resource: 'Look up what later papers say about a paper' via collected, classified citing sentences. This is clearly distinct from a generic literature search. It does not explicitly contrast itself with siblings like get_reception_report, so an agent must infer the boundary between per-citation statements and an aggregated reception view.

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?

Usage is implied by the phrasing 'what later papers say about a paper,' which suggests post-publication citation lookup rather than discovery. There is no explicit when-to-use or when-not-to-use guidance, and no mention of when get_reception_report or search_literature would be the better choice. The 'collecting, never as holding nothing' note functions more as behavior than routing guidance.

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