architecture_map

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

With no annotations provided, the description carries the full behavioral burden. It leads with 'Read-only,' clearly states the deterministic graph-based computation, discloses that labels are graph-derived member names rather than generated prose, and explains the edge-count/hub output. This gives an agent an accurate model of the tool's behavior and side effects.

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 compact sentences convey purpose, alternatives, pagination, and output semantics with zero filler. The read-only flag is front-loaded, and each phrase earns its place by either defining behavior or routing to sibling tools.

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 6-parameter, all-optional, no-output-schema tool, the description provides sufficient context: what is mapped, how results are structured, how to navigate paging, and which sibling tools to use in related cases. The schema covers parameter defaults and limits, while the description covers the conceptual and operational context needed to invoke the tool correctly.

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 parameters are already fully documented. The description adds value beyond the schema by clarifying that all params are optional and by explicitly mapping `offset` to community pagination and `file_offset` to per-community file pagination. This contextual paging semantics goes beyond the schema's minimal wording.

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 clearly states a specific verb ('Map') with a precise resource (the codebase's architecture) and defines the output as deterministic file communities over the call + dependency graph with edge counts and hubs. It explicitly differentiates itself from sibling tools by naming `communities` and `hubs` as the function-level and central-function alternatives.

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 gives explicit guidance on when to use this tool: as a directory-independent 'what are the big pieces' view, and when to use alternatives: `communities` for function-level subsystems and `hubs` for central functions. It also provides concrete invocation guidance with pagination semantics for `offset` and `file_offset`.

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