add_criterion

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

With no annotations, the description carries the full behavioral burden. It usefully discloses activation semantics ('the watcher picks it up on the next judged alert — no restart needed'), which is genuine value. However it says nothing about whether a new criterion starts enabled (a set_criterion_enabled sibling implies that matters), whether duplicates are rejected, persistence, or permissions.

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?

Front-loaded with purpose, then the rules-vs-criteria distinction, then authoring guidance, then args. Every sentence adds information rather than restating the name, though the prose is slightly longer than strictly necessary for a two-parameter tool.

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 two-parameter tool with no annotations and no output schema, the definition supplies purpose, activation timing, vocabulary disambiguation, and both parameter semantics — enough to call it correctly. The notable omission is the default enabled/disabled state of a newly added criterion.

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 0%, so the description must compensate, and it does: 'name' is explained as a 'short unique label, shown on matching alerts' (adding uniqueness and display semantics absent from the bare string schema) and 'description' as 'what qualifies, in plain language.' Both parameters gain meaning, though the effect of a non-unique name is not specified.

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 (add a criterion) and immediately clarifies the mechanism: 'the judge uses to decide whether a prefiltered post actually matters.' It explicitly distinguishes criteria from the sibling concept of rules ('Rules decide what gets looked at; criteria decide what gets surfaced'), so an agent can place it against add_alert_rule and list_criteria without opening schemas.

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?

Clearly frames when this tool applies (adding a triage criterion) and how it differs from rules, plus concrete guidance on how to author the criterion text with a good/bad example. It stops short of naming alternatives such as preview_rule for testing a criterion before adding it, or list_criteria for reviewing existing ones.

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