memory_recall

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states the tool is read-only and never mutates memory, which is a critical safety trait. It also describes the process (merging, deduplication, return format). Missing details about error handling, authentication, or rate limits, but the core safety behavior is transparent enough for a read-only query tool.

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 concise (4 sentences) and front-loaded with the main purpose. It uses backticks for code-like terms, is well-structured, and contains no fluff. Every sentence adds value, making it highly efficient for an AI agent to parse.

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 4 parameters and an output schema. The description covers the core operation (query, merge, deduplicate, return citations) and notes the read-only nature. However, it fails to explain the 'query', 'budget', and 'max_items' parameters, and does not detail the output schema structure beyond 'synthesis with citations'. This leaves gaps, but the overall context is minimally adequate.

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 explain all parameters. Only the 'banks' parameter is explained (default ['global-user']). The required 'query' parameter and optional 'budget' and 'max_items' parameters are not mentioned at all, leaving the agent without semantic guidance for those fields. This is a significant gap.

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 performs 'curated semantic recall across Hindsight banks', specifying it queries banks, merges results with provenance, deduplicates, and returns a synthesis with citations. This distinguishes it from sibling tools like memory_ingest_url (ingestion) and memory_dedupe (standalone dedup), making the purpose explicit and differentiated.

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 usage by listing the operation (query, merge, deduplicate, return citations) and explicitly states 'Read-only; never mutates memory', which guides safe invocation. However, it lacks explicit when-to-use versus alternatives (e.g., memory_reroute) and does not provide exclusions or prerequisites, so the guidance is clear but not exhaustive.

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