mcp-server-ads

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

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds behavioral context by specifying that it returns 'papers that are frequently co-cited' and excludes those 'not yet included,' which clarifies the recommendation logic. However, it lacks details on rate limits, response format, or potential errors, leaving some behavioral aspects uncovered.

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 front-loaded with the core purpose in the first sentence and follows with a clarifying second sentence. Every sentence earns its place by defining the input, output, and logic without redundancy. It is appropriately sized, avoiding unnecessary details while being fully informative for the tool's scope.

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?

Given the tool's moderate complexity (citation recommendation based on co-citation), annotations cover safety, schema covers the single parameter, and an output schema exists (though not detailed here). The description adequately explains the tool's function and logic. However, it could be more complete by hinting at output structure or usage constraints, but the presence of an output schema reduces the need for such details, making it nearly sufficient.

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%, with the parameter 'bibcodes' fully documented in the schema as 'List of bibcodes already in the bibliography.' The description reinforces this by mentioning 'a set of bibcodes (e.g. from a paper's bibliography),' adding minimal semantic value beyond the schema. Since coverage is high, the baseline score of 3 is appropriate, as the description does not significantly enhance parameter understanding.

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 clearly states the specific verb ('suggest papers that should be cited') and resource ('papers'), and distinguishes it from siblings by focusing on citation recommendations rather than search, export, or metrics. It explicitly defines the input as 'a set of bibcodes (e.g. from a paper's bibliography)' and the output as 'papers that are frequently co-cited with the input set but are not yet included,' making the purpose distinct and well-specified.

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?

The description provides clear context for when to use this tool: 'Given a set of bibcodes (e.g. from a paper's bibliography),' implying it's for enhancing bibliographies. However, it does not explicitly state when not to use it or name alternatives among sibling tools (e.g., ads_search for general paper discovery), which limits guidance on tool selection in broader workflows.

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