git_sins

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'read-only', which is a critical safety signal for an agent deciding whether to invoke the tool. It also discloses the output format (markdown confession) and the scoring mechanism (0-100 Sin Score), which helps the agent set expectations. It doesn't mention performance on large repos or whether it requires network access, but for a read-only analysis tool, the key behavioral trait (non-mutating) is clearly disclosed.

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, well-crafted sentence that front-loads the core purpose ('confession booth for a git repository'), then packs in the key details (read-only, examples of what it detects, output format, scoring). Every clause earns its place, and the playful tone doesn't obscure the technical meaning. It's appropriately sized for a tool with only 2 parameters and no output schema.

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 read-only analysis tool with 2 parameters, full schema coverage, and no output schema, the description is nearly complete. It tells the agent what the tool does, what it returns, and that it's safe (read-only). The only gaps are minor: it doesn't specify whether the repo path must be absolute or relative, and it doesn't mention edge cases like empty repos or uncommitted changes. But these are not critical for an agent deciding whether to call 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 description coverage is 100%, so the schema already documents both parameters ('repo' and 'share'). The description adds context by explaining the 'share' parameter's purpose ('Append a shareable badge block') and implies that 'repo' is a local path. The description's mention of 'markdown confession' hints at what the output looks like, which complements the schema. It doesn't add syntax details, but with full schema coverage, the baseline is 3, and the description's contextual hints push it to 4.

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 vivid metaphor ('confession booth') but immediately grounds it with a specific verb ('Analyzes the history read-only'), a specific resource (git repository), and concrete examples of what it detects (3 AM commits, 'wip' messages, mega-commits, TODO graveyards, zombie branches). It also states the output format (markdown confession with evidence, penance, and a 0-100 Sin Score), making the tool's purpose unmistakable. The sibling tools (container_autopsy, container_obituary) are clearly different domains, so there's no ambiguity.

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 when to use this tool: when you want a read-only analysis of a git repository's history, with a playful but structured report. It doesn't explicitly name alternatives or exclusions, but the sibling tools are about containers, not git, so the context is clear. The 'read-only' qualifier is a useful usage signal. It could be improved by stating when NOT to use it (e.g., if you need to modify history or if the repo is not local), but the context is strong enough.

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