pscribe_tail

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

With no annotations, the description carries the full burden. It thoroughly discloses the TOON output format, field meanings, dedup behavior ('keeping confirmed over unconfirmed'), and the nuance that 'last_line metadata reflects raw line count before dedup.' It also explains mutual exclusivity and the polling workflow, exceeding typical transparency expectations.

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 dense yet well-organized: a single-sentence purpose, a bulleted format explanation, and concise usage notes. No sentence is wasted; all information is relevant and directly supports correct invocation.

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?

Given no output schema and no annotations, the description must explain return values and behavior itself. It thoroughly covers the TOON format, each field, status filter semantics, dedup behavior, and polling usage. This makes the description complete for a 5-parameter tool with no structured metadata beyond the input 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?

Though the schema already covers all 5 parameters (100% coverage), the description adds meaningful context beyond the schema: n and since_line are mutually exclusive, since_line enables a polling pattern, and dedup has a metadata caveat. This is exactly the kind of relational and usage nuance that schemas cannot convey.

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 'Get recent transcript entries,' which is a specific verb+resource combination. The 'recent' scope hints at differentiation from sibling list/search tools, but it does not explicitly name alternatives like pscribe_cat or pscribe_grep, so it falls short of full sibling differentiation.

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 explicit guidance on using 'n' for last N lines and 'since_line' for polling, including a step-by-step polling pattern: 'call with since_line, note the last line number, then call again with that number + 1.' However, it does not discuss when to choose this tool over siblings, leaving the alternatives unmentioned.

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