get_state

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It explains the exact retrieval logic: scoping to current git branch, falling back to default branch, then to legacy flat file, and how global memory is merged with precedence rules. It also implies a non-destructive read operation ('Returns'), and details the deduplication of global memory, which is transparent and actionable.

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 four sentences, each adding necessary detail: first defines what is returned, second explains scoping, third explains global memory handling, and fourth gives usage timing. It is front-loaded with the core purpose and avoids redundancy or fluff. Despite covering complex behavior, it remains tight and efficient.

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 there is no output schema, the description must clarify what the caller receives. It explicitly lists content types (decisions, preferences, things to avoid, next steps), describes the structural sections (project state, Global Memory), and explains precedence and deduplication. It also covers edge cases like git vs non-git environments and global memory existence, making it complete for a state-fetching tool.

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?

There is only one parameter, project_path, and its schema description already covers the default behavior ('Defaults to current working directory') with 100% schema description coverage. The tool description adds no additional information about the parameter, so the baseline score of 3 for high coverage is appropriate.

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 the tool returns 'the current project memory' and enumerates its contents (decisions, preferences, things to avoid, next steps). It also specifies scoping behavior to git branches, fallback order, and inclusion of global memory, making it distinct from siblings like get_project_state or working_memory_list. The verb 'Returns' with a concrete resource is specific and actionable.

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 an explicit usage instruction: 'Call this at the START of every session to restore context.' It also provides contextual guidance by explaining how global memory is written (via update_state with scope 'global'), which helps understand when this tool is appropriate. While it doesn't explicitly name alternatives, the call-to-action and scoping details offer clear guidance on when to use it.

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