memory_signal

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

Annotations only say readOnlyHint=false (write operation), but the description adds that it 'Appends to the filesystem', is 'rate-limited per (type, path) within a rolling window', and 'Returns the recorded signal'. This clearly discloses side effects and constraints beyond the annotation, with no contradiction.

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 focused sentences: front-loaded with the action and destination, followed by usage context, behavioral details, and return value. Every sentence adds value, with no redundancy or fluff.

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 is simple with 3 required params and no output schema. The description covers purpose, target file path, append behavior, rate limiting, and return value, which is complete for an agent to decide when and how to invoke the tool.

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% with descriptions for all three parameters (type, path, body). The description adds general context like 'short, anchored observation' and 'tied to a specific file' but does not provide additional per-parameter semantics beyond the schema. Baseline 3 is appropriate.

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 uses the specific verb 'Record' with a resource ('engineering-memory signal') and a concrete destination (the monthly intake log). It distinguishes from sibling memory_lookup by stating this captures learnings so future lookups can surface them, making the tool's role clear.

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 states when to use it ('Use to capture a learning tied to a specific file') and gives examples (recurring bug pattern, ownership note). It implies the read counterpart is memory_lookup but does not explicitly exclude alternatives, which prevents a 5.

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