trace_rpc

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

Adds important context beyond annotations: 'Snapshot-strict' indicating consistency, and internal steps (searchSchemaObjects, etc.). No contradiction with readOnlyHint=true and idempotentHint=true.

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?

Well-structured with a front-loaded purpose and colon-separated details. Slightly dense but efficient; every sentence adds value.

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?

Covers main outputs but lacks detail on output schema (though it exists) and parameter relationships. Does not explain how argTypes disambiguates overloads or when schema is needed.

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%, yet the description does not explain the purpose of individual parameters (projectId, projectRef, schema, argTypes). Only mentions the function name placeholder, leaving agent to guess parameter roles.

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?

Clearly defines 'Trace an RPC end-to-end' with specific sub-components (definition, bodies, table refs, app-code). Distinguishes from sibling tracing tools like trace_table or trace_edge by focusing on RPC-specific aspects.

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?

Implies usage for tracing an RPC but provides no explicit when-to-use or when-not-to-use guidance. Does not compare with sibling tools like rpc_neighborhood or trace_error.

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