Search remembered project history

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

With no annotations provided, the description carries the full behavioral disclosure burden. It does reveal a key trait—output is a token-budgeted, ranked context block rather than raw results—and lists data sources. Yet it does not state whether the operation is read-only, whether special permissions are required, or how edge cases like the asOf semantics behave, leaving some ambiguity.

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 two sentences, front-loaded with the verb and resource, and packs in the content-type list and the critical behavioral contrast at the end. Every clause adds value, with no redundancy or 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?

For a complex search tool with no output schema, the description covers the core semantics: what is searched, what is returned, and the ranked/budgeted nature of the result. It doesn't detail the exact structure of the context block or error conditions, but the high-level guidance is sufficient for an agent to select and invoke the tool correctly.

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?

The schema provides 100% description coverage for all five parameters, so the description need not add much. It echoes the 'token-budgeted' notion from the schema but does not elaborate on parameter constraints or relationships. The baseline of 3 is appropriate since the schema already carries the heavy lifting.

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 a specific verb ('Search') and resource ('NexMem-tracked repository's remembered history'), then enumerates the exact content domains covered (git commits, diffs, shell commands, docs, transcripts, issue/PR threads). It also clarifies the return type is a token-budgeted ranked context block, which differentiates it from sibling tools like list_recent_memory even without naming them.

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 clearly communicates the intended use—searching a repository's remembered history—and lays out the breadth of content searched, which helps an agent decide when to invoke it. However, it does not explicitly contrast with sibling tools or state when NOT to use it, so it falls short of the top score.

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