get_architecture

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

With no annotations at all, the description carries the full disclosure burden. 'Return' implies a read-only, side-effect-free operation and it names the source file and the summarized fields, but it says nothing about permissions, mutation risk, or failure behavior when the state file is missing.

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 sentences, zero waste, and the most important content (what is returned and where from) is front-loaded before the usage cue. Every clause 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, so the description usefully compensates by naming the returned contents (record count, validation summary, decision log length). For a single-optional-parameter read tool this is largely sufficient; only error/absence handling is left unspecified.

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% and the single parameter (state_path) is already documented in the schema, including its default. The description's mention of .aimdb/state.toml merely repeats that default, adding no syntax or format detail beyond the structured field.

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+resource ('Return the current architecture state from .aimdb/state.toml as structured JSON') and even enumerates the payload contents. It is clearly distinguishable from mutating siblings like set_record or propose_* tools, though it does not explicitly separate itself from other read tools such as get_instance_info or list_records.

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?

Gives an explicit trigger condition: 'Run this first when entering an architecture session.' That is a concrete when-to-use cue. It stops short of stating when not to use it or naming an alternative tool, which keeps it out of 5 territory.

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