suggest_next_actions

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

Beyond annotations (readOnlyHint=true, idempotentHint=true, etc.), the description adds behavioral traits: 'No LLM calls - uses a static decision tree for instant responses' and 'No prior indexing required.' This clearly informs the agent about the tool's non-LLM nature and lack of indexing needs, which are not captured in 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 three sentences long, front-loading the core purpose and output, then clarifying key behavioral aspects (no LLM, static decision tree, no indexing). Every sentence adds value with no redundant information.

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?

With annotations covering safety (read-only, idempotent) and schema covering parameters, the description adds the no-LLM and no-indexing context. It lacks details on return format (e.g., structure of 'ranked suggestions') but that is partially described. Given the low complexity (3 optional params), the description is largely complete.

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 clear descriptions for all three parameters (tools_used, context, repo_path). The description does not add extra parameter details beyond what the schema provides, so a baseline score of 3 is appropriate given the schema already does its job.

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's purpose: 'Suggest which tools to use next based on tools already used. Returns ranked suggestions with reasons.' This provides a specific verb and resource, and the mention of 'No LLM calls' distinguishes it from sibling tools like 'ask_question' or 'deep_research' that might involve LLM-based reasoning.

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 implies when to use by stating 'No LLM calls - uses a static decision tree for instant responses' and 'No prior indexing required,' suggesting it's for quick, lightweight suggestions. However, it does not explicitly state when not to use or name alternative tools, leaving some ambiguity for agents.

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