intent_save

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

With no annotations, the description carries the full behavioral burden and does disclose one genuinely important trait: 'Same name replaces', i.e. this is an upsert that silently overwrites an existing intent. It also states the 6-hint cap. It says nothing about permissions, whether the overwrite is recoverable, or what happens on an invalid run id.

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?

One dense sentence, front-loaded with the verb and resource, with no filler. The telegraphic 'Same name replaces' is terse to the point of being slightly cryptic, which keeps it from a 5.

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 5-parameter mutation tool with no annotations and no output schema, the definition covers the payload shape and the overwrite behavior but omits the return value, error conditions, and any note that omitting 'steps' defaults to every replayable step (that detail lives only in the schema).

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 coverage is 40%, so the description must compensate and partly does: it clarifies that 'name' is the replacement key, that 'hints' is capped at 6, and that 'steps' are replayable step numbers of a run. 'from_run' is only obliquely covered by '(from history)' and relies on its own schema text.

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 specific verb ('Save') and resource ('an intent') and enumerates the payload: a short prompt, up to 6 hints, and replayable steps from a run. That is enough to distinguish it from the read-oriented siblings intent_list and intent_show, though it never names them.

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?

'Save what worked' implies the usage context (after a successful run worth replaying) and '(from history)' points at where run ids come from, but there is no explicit when-not guidance or named alternative such as intent_show for inspecting existing intents.

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