get_snapshot

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: verification is rechecked against sampled source contents, stale/unknown verification forces a fresh review, and recordedVerdict preserves the historical verdict. It still doesn't explicitly say the call is read-only or whether the recheck itself touches source files, but the behavioral picture is unusually rich.

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?

It is front-loaded with the primary purpose, and each sentence carries information about return shape, verification staleness, or prerequisites. The mention of get_context and get_impact is slightly tangential but still useful for scoping, and the jargon density is tolerable.

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 one-parameter read tool with no annotations and no output schema, the description covers the important return cases (exists:false, recordedVerdict) and prerequisites. The only real gap is the shape of the map itself when it does exist, which an agent might want spelled out.

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 single parameter 'dir' has 100% schema description coverage ('Absolute path to the project root directory'), so the schema already does the work. The description adds nothing about the directory argument; baseline 3 applies.

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 first sentence states a concrete verb and resource: return the feature-to-file architecture map with drift and trust evidence. That clearly separates it from mutation siblings like save_snapshot or verify_snapshot, though the description never names those siblings explicitly, so differentiation is inferred rather than stated.

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 gives useful boundary conditions ('If no map exists, returns exists:false', 'No initialization required') and notes that decision capture, get_context, and get_impact keep working without a map. However, it never states when to call this versus verify_snapshot or save_snapshot, so the routing guidance is only implied.

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