palinode_save

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

Annotations declare it is a non-read-only, non-idempotent, non-destructive write. The description adds a genuinely non-obvious behavioral trait beyond annotations: a timeout may still have committed, so retrying can duplicate. This directly explains the consequence of idempotentHint=false and is highly actionable. It does not cover auth or return semantics, so not a 5.

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 sentences, purpose front-loaded, then the calling constraint, then the failure-mode protocol. Every sentence carries load and there is no filler.

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 19-parameter tool with nested objects and no output schema, the description covers the critical call-time traps (type/ps exclusivity, timeout duplication risk), and the rich 100%-covered schema handles the rest. It does not hint at the more advanced features (claims, contradicts, update_policy), but the schema documents them adequately, so completeness is strong though not maximal.

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 schema already documents all 19 parameters including the type/ps mutual exclusion and the epistemic/priority semantics. The description's 'exactly one of type or ps=true' restates what the schema's ps/type descriptions already say, adding no new parameter meaning. Baseline 3 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?

States a specific verb+resource ('Save a memory') and enumerates what qualifies as a memory (fact, decision, insight, project update). It also names the sibling palinode_search in the retry path, which helps an agent distinguish the write tool from the read/search tools.

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 clear usage context ('worth keeping across sessions'), a hard calling constraint ('Requires exactly one of type or ps=true'), and an alternative action on timeout ('palinode_search a distinctive phrase before retrying'). It lacks explicit when-not guidance (e.g., prefer dedup_suggest or consolidate first), so it falls short of a 5.

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