save_session

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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that the tool is non-destructive ('without ending the session') and that it falls back to the current project. However, it does not disclose whether saving overwrites existing state, merges data, requires permissions, or what the response contains. Some useful traits are provided, but significant gaps remain.

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 two short sentences that get straight to the point. It front-loads the core purpose, then adds a key default behavior and an optional field note. No waste or redundancy.

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?

While the schema documents all 9 parameters, the description provides limited context for a tool with no annotations or output schema. It explains the project default and mentions embodiment, but it does not clarify how other fields (notes, summary, blockers) are handled, whether state is overwritten, or what happens on success. It is adequate but not fully complete for the tool's complexity.

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 baseline is 3. The description reinforces the project default and highlights 'embodiment' as optional, but the schema already provides these details (e.g., 'uses current project if omitted' for project). No new semantic meaning is added beyond the schema.

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's function: 'Save session state without ending the session.' This specifies the verb (save), the resource (session state), and explicitly distinguishes it from ending a session, which differentiates it from sibling tools like end_session. It also mentions the project default behavior, adding scope.

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 clear context: it saves state mid-session (not ending it) and uses the current project if none is specified. This implies when to use it, but it does not explicitly contrast it with alternatives like update_session_progress or provide exclusion criteria. It is useful but could be more explicit about when not to use it.

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