search_decisions

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

With no annotations, the description must fully disclose behavior. It does explain the priority order for project identifiers (project_id > workspace_path > project_name) and mentions you can specify any combination. However, it does not clarify how query and tags interact (AND vs OR), what fields are returned in results, or why the project lookup sentence is included. This leaves room for uncertainty.

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 with a clear opening sentence, a priority note, and structured WHEN TO USE/USEFUL FOR sections. While it is moderately long, every section contributes meaningful guidance. The USEFUL FOR section is slightly redundant with WHEN TO USE but not excessively so.

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 tool has 5 parameters and no output schema, so the description must cover more ground. It explains the core purpose, usage scenarios, and identifier priority, but omits details about result structure, filtering behavior with tags, or potential edge cases. This leaves some gaps but still provides a usable baseline for an agent.

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?

Input schema descriptions already cover all parameters with 100% coverage, so baseline is 3. The description adds extra value by explicitly stating the resolution priority for project identifiers and providing example tag values, giving users a clearer mental model of precedence and usage.

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 'Search through recorded decisions by keywords or metadata' and the WHEN TO USE section reinforces specific decision-related use cases. This distinguishes it from sibling tools like get_project_decisions, which likely list all decisions without keyword search. The initial phrase 'flexible project lookup' adds slight ambiguity but does not undermine the core purpose.

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 WHEN TO USE section provides explicit scenarios with concrete examples (e.g., 'Looking for decisions about specific topics', 'Checking if a particular technology was already decided upon'). It does not explicitly name alternatives, but the context makes it clear this is the right tool for targeted decision search rather than general project listing.

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