suggest_connections

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

Without annotations, the description bears full burden. It explicitly states the tool is read-only ('never creates connections'), which is critical behavioral info. It also mentions the output limit (up to 5). More detail on error handling or scope would improve, but the key safety aspect is well-covered.

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 two concise sentences, front-loading the action and then adding usage guidance and behavioral note. Every sentence adds value with no redundancy.

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 has 2 parameters and no output schema, the description adequately explains what it does and what to expect (up to 5 candidates with overlapping attributes). It could be more complete about output format or matching details, but it's sufficient for most agents.

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 baseline is 3. The description adds meaning by explaining the 'id' parameter as 'Given a node ID' and the 'limit' as 'up to 5'. It also adds context on matching criteria ('labels, descriptions, or tags'), going beyond schema.

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 tool returns candidate connections for a given node ID based on overlapping labels, descriptions, or tags. It uses a specific verb ('return') and resource ('candidate connections'), and the criteria (labels, descriptions, tags) distinguish it from siblings like 'connect' or 'why_connected'.

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 guides when to use the tool: 'Use this after filing a memory to discover likely connections before calling connect.' This provides clear context and an alternative (calling connect after). However, it does not mention when not to use it or handle edge cases.

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