get_repository_snapshot

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

No annotations are provided, so the description bears the transparency burden. It discloses that the snapshot is bounded and normalized, and that it skips the full analysis pipeline, which is useful. However, it does not explain what 'bounded' concretely means (e.g., maxFiles), how source content is selected, or any rate limits or side effects. This is a read-oriented tool, so the lack of destructive-warning detail is less critical, but more specificity would improve transparency.

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-structured sentence that front-loads the primary action and key qualifiers. It earns its place by conveying the core purpose and the distinguishing contrast without unnecessary words.

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 the absence of an output schema and annotations, the description needs to explain both inputs and expected outputs. It lists snapshot components (file tree, manifest, README, selected source content) and notes boundedness, but is vague about what 'selected source content' means and what the return format looks like. For a tool with nested parameters and no output schema, this is adequate but leaves meaningful gaps.

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 67%—repo and branch have descriptions, while options does not. The description adds context by mentioning 'README' (relating to includeReadme) and 'bounded' (implying maxFiles), but it does not explicitly map these to the parameter names or explain the nested options structure. It adds some value but does not fully compensate for the missing schema description of options.

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 'Return' and clearly identifies the resource (a bounded, normalized repository snapshot) with concrete contents (file tree, manifest, README, selected source content). It also distinguishes itself from siblings by explicitly stating it runs 'without the full analysis pipeline,' which differentiates it from tools like analyze_evidence_profile.

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 provides clear context for use: when a quick, bounded snapshot is needed instead of a full analysis pipeline. It implies a lighter-weight alternative but stops short of explicitly naming sibling tools or stating when not to use it. The 'without running the full analysis pipeline' gives strong contextual signal.

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