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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds valuable behavioral context beyond annotations: it specifies the data source (CORDIS linked-data knowledge graph), the scope (283,000+ journal papers and 92,000+ proceedings papers from Horizon/H2020 research), and the return fields (publication identifier, full title, DOI, publication date, RCN of parent project). This gives the agent a clear picture of what to expect without contradicting the annotations.

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 compact and information-dense, with no wasted words. It front-loads the core purpose in the first sentence, then efficiently covers filtering options, return fields, and data scale in subsequent sentences. Every sentence earns its place, and the structure is easy to parse for an agent.

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?

The description is complete for a read-only search tool: it covers what the tool does, how to filter, what fields are returned, and the data scope. The output schema exists, so return values are already structured. The only minor gap is that it doesn't explicitly state pagination behavior or what happens when no results are found, but these are not critical for a search tool with a limit parameter and read-only annotations.

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 three parameters (limit, query, project_id) with descriptions and examples. The tool description adds some context by explaining the relationship between query and project_id (filter by keyword OR scope to a project), but it doesn't add significant new meaning beyond what the schema provides. The baseline of 3 is appropriate since the schema carries 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 states a specific verb ('Search') and resource ('research publications linked to EU-funded projects in the CORDIS linked-data knowledge graph'), and clearly distinguishes it from sibling tools like cordis.research.project_search and cordis.research.project_details by focusing on publications. It also specifies the publication types covered (journal papers, conference proceedings), making the tool's purpose unambiguous.

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 explicitly explains the two primary usage modes: filtering by keyword in the publication title, or scoping to a specific project via grant agreement number. It also provides concrete examples of query values and the project_id format, which helps an agent decide when to use this tool versus alternatives. While it doesn't explicitly name sibling tools, the context signals show related CORDIS tools (project_search, project_details, organisation_search), and the description's focus on publications makes the usage context clear.

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