search_sessions

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

With no annotations present, the description carries the full burden and delivers: it discloses date inclusivity/exclusivity, scope clamping behavior, ownership metadata in results, and the return contents. It also warns agents not to automatically call summarize_session afterward, which is a behavioral guardrail beyond what structured fields would indicate.

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 longer than the ideal two-sentence form, but the length is justified by the tool's complexity and the need to document ambiguous parameters and sibling routing. It is well-structured: purpose first, then usage conditions, parameter semantics, and follow-up guidance. A few sentences could be tightened, but none are filler.

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 seven parameters, no annotations, and multiple sibling tools, the description is remarkably complete. It covers when to use the tool, how to handle each parameter, what the backend does, what results look like, and how to continue the workflow with search_by_filename. The presence of an output schema also means the return-value description is a bonus, not a requirement.

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 for all seven parameters. It does so well for file_path, scope, date_from, date_to, project_name, and query implicitly via 'by intent'. The only omitted parameter is limit, which is left to inference from 'Returns ... up to three changed source files' despite being a tunable result cap.

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 opens with a specific verb and resource: 'Search prior ReclaimLLM sessions by intent using backend hybrid semantic plus BM25 search.' It clearly distinguishes this tool from search_by_filename and other siblings by focusing on semantic intent search, so an agent can tell it apart without inspecting schemas.

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 states when to use this tool ('when the user hints that similar prior work may exist' or for bug fixes/performance improvements), when not to retry, and names the alternative tool for file/folder history searches (search_by_filename). It also gives follow-up guidance to use search_by_filename on returned changed_files paths, which is unusually actionable.

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