encode-toolkit

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

Annotations indicate readOnlyHint=false (mutation), openWorldHint=false (closed system), idempotentHint=true (safe to retry), and destructiveHint=false (non-destructive). The description adds valuable context beyond this: it calls this a 'cross-server bridge' for provenance, mentions use cases like linking papers from PubMed MCP, and implies it's for future reference tracking. However, it doesn't specify authentication needs, rate limits, or error behaviors, leaving some gaps in behavioral disclosure.

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 well-structured and front-loaded: it starts with the core purpose, expands with context and examples, includes dedicated sections for usage guidelines and related tools, and ends with parameter and return explanations. Every sentence adds value—no fluff or repetition. The formatting with clear sections enhances readability without unnecessary verbosity.

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 complexity (mutation with 4 parameters, 0% schema coverage, and an output schema), the description is highly complete. It covers purpose, usage, parameters with examples, related tools, and mentions returns ('JSON with linking result'), leveraging the output schema. With annotations providing safety hints and the description filling in gaps, it offers a comprehensive view for an agent to invoke this tool correctly.

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 provides detailed semantics: experiment_accession is explained with an example ('ENCSR133RZO'), reference_type lists all enum values with examples (e.g., 'pmid' as '32728249'), reference_id is described as 'The actual identifier value', and description is noted as 'Optional description of why this reference is linked'. This adds substantial meaning beyond the bare schema, though it doesn't cover validation rules or format specifics for each type.

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 action ('Link an external reference') and resource ('to a tracked ENCODE experiment'), distinguishing it from siblings like encode_get_references (which retrieves references) and encode_get_citations (which likely retrieves citations). It explicitly mentions what types of external identifiers can be linked (PubMed IDs, DOIs, etc.), making the purpose highly specific and differentiated.

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 includes an explicit 'WHEN TO USE' section that states to use this tool 'to attach external IDs (PMID, DOI, GEO, NCT) to tracked experiments for cross-referencing.' It also lists 'RELATED TOOLS' (encode_get_references, encode_get_citations), providing clear alternatives for retrieval rather than linking. This gives comprehensive guidance on when to use this tool versus others.

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