Guard Context

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

With no annotations, the description carries the full burden; it does disclose that the tool reads a persisted snapshot by default and can rediscover the working tree, plus that it functions before init. It does not clarify whether on-demand discovery writes/persists a snapshot (a possible side effect), nor anything about cost, caching, or failure modes when no project is found.

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 short sentences, zero filler, with the core capability front-loaded and the pre-init capability as a secondary clause. Everything present earns its place.

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?

There is no output schema and no annotations, so the description is the only source of behavioral detail; it covers what is read and the pre-init case but omits return structure, any write/persist side effects of discovery, and error behavior. Adequate to start, but not complete for an agent deciding whether calling it is safe or expensive.

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 100% and both parameters are documented in-schema, so the baseline is 3. The description only echoes the refresh behavior (rediscover vs persisted snapshot) without adding format, cost, or default-related nuance beyond the schema's own description.

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?

States a specific verb (read) and concrete resources (project model, architecture insights, local rules) scoped to Codapult Guard. It is clear what comes back, though it doesn't explicitly contrast itself with close siblings like guard_analyze or guard_explain, which also surface project understanding.

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?

"Works before init by discovering the project on demand" gives one useful usage condition (callable pre-init, no prior setup). However there is no guidance on when to prefer this over siblings such as guard_init (which presumably persists context) or guard_analyze, leaving selection largely to inference.

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