Session save

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

Annotations declare non-read-only, non-destructive, closed-world, but do not say what persistence semantics to expect; the description adds that it appends (rather than replaces), that a session id comes back, and that old sessions expire after SESSION_RETENTION_DAYS. It does not say whether appending to an existing session merges or overwrites a prior summary, which is the one behavioral detail left open.

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?

Three short sentences, each carrying distinct information, with the core operation and its purpose front-loaded and the retention caveat last. No restatement of the name or title.

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?

An output schema exists and annotations carry the safety profile, so the description only needs the handover intent, the memory_write boundary and retention, all of which are present. What remains thin is session lifecycle detail, such as what happens when a session_id is reused or a title collides, but nothing needed to invoke it correctly is missing.

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 every parameter including model, title, project, status, summary, next_steps and session_id is already documented in the schema. The description's mention of resume-by-another-device and the returned session id adds framing but no new syntax or format detail beyond what the schema states.

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 gives a concrete verb and resource ('Append a checkpoint to a work session') plus the reason it exists ('so another LLM/device can resume it'). It also separates itself from the sibling memory_write in the same breath, so an agent can route without opening a schema.

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?

'For handing over work in progress; durable facts belong in memory_write' states both the intended use and the alternative with the condition that selects it. The routing decision between persistent memory and transient session checkpoints is explicit rather than implied.

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