remember_commit_digest

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

With no annotations provided, the description must carry the burden of behavioral disclosure. It uses 'Get' implying a read-only operation, and the note that 'The AI writes the actual summary' indicates the tool does not itself write to memory. However, it does not mention potential errors (e.g., invalid refs), authentication requirements, or any side effects. This is adequate but not rich.

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 a single, dense sentence that front-loads the core purpose ('Get a formatted commit log + changed-files summary of base..head') and then adds usage context. Every phrase earns its place, with no fluff. It is appropriately concise and well-structured.

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 there is an output schema (context signals say 'Has output schema: true'), the description need not explain return values. It covers the tool's purpose, the expected usage context (to feed into save_note/log_decision), and the source ('YOUR CODE repo'). However, it lacks details about what happens with invalid refs or any prerequisites, leaving a small gap. Overall, it is fairly complete for a read-only tool, just not exhaustive.

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. It mentions 'base..head' which hints at the parameters, but does not explain that base_ref is required or that head_ref defaults to HEAD. The meaning of base/head is not explicitly defined, leaving some ambiguity for an agent. The description provides minimal added value beyond the parameter names themselves.

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 it gets a formatted commit log + changed-files summary of base..head from the code repo. It names the specific resource and action, and distinguishes itself from siblings like save_note/log_decision by noting the output is 'ready to summarize' into those tools. It is not a tautology and explains the tool's purpose precisely.

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 gives clear context: it is used to fetch commit data that will be summarized into a note or decision with save_note/log_decision. It implies when to use it (before those tools) but does not explicitly state when not to use it or name alternatives like git_blame_context. The 'from YOUR CODE repo' adds specificity. Overall, it provides clear context but lacks explicit exclusions.

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