investigate

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it discloses that output is evidence only and explicitly that it will not assert a root cause, which shapes how the agent should treat the result. It still omits output format and pagination/breadth details, keeping it at a 4.

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 sentences with zero filler: the first front-loads the purpose and evidence sources, the second front-loads the output contract. It is appropriately sized, though a brief clause clarifying scope or prerequisites could be added without bloat.

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 complex six-parameter aggregator with no output schema and 0% parameter description coverage, yet the description does not explain how question and repo_path drive the investigation, what each search parameter does, or what the returned evidence looks like structurally. Annotations cover safety, but the description leaves too much unspecified for an agent to invoke it confidently in edge cases.

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% across six parameters, so the schema itself adds no semantic help. The description's enumerated sources (commits+diffs, code search, log search, test results) only loosely hint at some parameters like since, search_query, log_path, and log_query, and it says nothing about repo_path, question, or formats such as the '30d' default for since. This is a substantial compensation gap for a 6-parameter tool.

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 ('Gathers evidence') and enumerates the exact resources collected (recent commits + diffs, code search, log search, test results), which clearly distinguishes it as an aggregator rather than a single-source tool like git_diff or search_logs. It stops short of explicitly stating how it relates to those individual siblings, so it earns a 4 rather than a 5.

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?

It frames the intended context ('relevant to an engineering question') and sets a clear output boundary ('returns evidence only ... reason over the returned evidence yourself'), which implicitly tells the agent when this broad evidence-gathering tool is appropriate. However, it never names alternatives or says when NOT to use it versus calling recent_changes, search_code, or search_logs directly, leaving usage guidance at an implied level.

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