git_blame

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is clear. The description adds a small behavioral detail ('line-level') but does not disclose nuances like whether line numbers are inclusive, how revision affects the output, or if any file-state prerequisites exist. Still, it does not contradict annotations and adds a bit of context beyond the raw facts.

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?

One sentence, front-loaded with the action, and zero wasted words. It is appropriately sized for a tool that performs a single, well-known operation. The structure is ideal for quick scanning by an agent.

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?

While an output schema exists (so return values need not be explained), the description lacks enough context for correct invocation given the low schema description coverage. It omits any information about line range semantics, revision behavior, or how the tool behaves across different repository states. An agent may not know that start/end are optional, or what revision defaults to, without deeper inference.

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 only 20% (only repositoryId has a description), and the tool description does not compensate. It mentions 'a file' (implying path) and 'line-level' (implying start/end), but does not explain the semantics of start, end, or revision (beyond the default of HEAD). The description leaves most parameters under-documented, forcing the agent to rely on schema types and defaults.

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 ('Show') and clearly identifies the resource ('line-level commit attribution for a file'). It distinctly separates this from sibling tools like git_log (which shows commit history) or git_diff (which shows changes between revisions), so an agent can unambiguously select git_blame for line-attribution needs.

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 a use case (inspecting line-level history of a file) but does not explicitly state when to use it instead of alternatives or any preconditions. It lacks guidance on when not to use it (e.g., when needing only commit-level history). This is typical of a minimal but non-misleading description.

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