search_decisions

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description indicates this is a read/search operation but doesn't state return format details, pagination behavior, or whether results are sorted. However, since an output schema exists and this is a standard search tool, the description is minimally acceptable for a safe read operation.

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?

Two short sentences, front-loaded with the core purpose and a brief elaboration. Very efficient with minimal waste, though the second sentence adds marginal value by stating the obvious ('search for decisions made in meetings by text').

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?

This is a simple search tool with full schema coverage and an output schema. The description states what it searches (decision log, decisions by text) but doesn't clarify how it differs from sibling tools like search_follow_ups or search_commitments, nor does it specify whether partial matching or exact matching is used. For a straightforward search tool this is adequate but not rich.

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 coverage is 100% — both parameters (limit and query) are described in the input schema with defaults noted. The description adds the context that 'query' is a text search against decisions, which aligns with the schema. Baseline 3 is appropriate since the schema already handles parameter documentation.

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 has a clear verb+resource ('Search the decision log') and adds context about searching decisions by text from meetings. It correctly identifies the resource (decisions) and distinguishes the action (search). However, it doesn't explicitly distinguish from closely-related sibling tools like search_commitments or search_follow_ups beyond the 'decisions' resource.

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 this is used to find decisions via text search but provides no explicit when-to-use guidance or contrast with alternative tools like get_recent_decisions or get_meeting_decisions (which likely provide non-search retrieval paths). No exclusions or caveats about query format or use cases.

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