BPJ Task Loop

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose scope – what is included (tools, capabilities, availability) and excluded (third-party directory) – which is meaningful context beyond the name. It stops short of describing return format, pagination, or any auth/rate-limit considerations, leaving gaps for a no-annotation tool.

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?

Two short sentences, zero filler. The primary purpose (listing first-party BPJ AI workflow tools) is front-loaded, with the scoping clarification second.

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 zero-parameter listing tool with no annotations and no output schema, the description covers the essentials: what is enumerated (tools, capabilities, availability) and the scope boundary. Richer detail on return structure would help, but there is little an agent needs beyond this to invoke it correctly.

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?

The schema has zero parameters, so per the baseline rule a 4 is appropriate. There is no parameter syntax to explain, and the description's mention of 'capabilities and availability' roughly characterizes the fields returned rather than any inputs.

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 ('List') and a precisely scoped resource ('first-party BPJ AI workflow tools, capabilities and availability'). It also clarifies the boundary against a third-party directory, which sharpens what this tool is not. It does not name the sibling tool review_task_state, but that sibling is in an unrelated domain, so the lack of differentiation is minor.

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 phrase 'Separate from third-party directory' implies the condition for selecting this tool (first-party inventory rather than third-party listings), which is useful implicit guidance. However, it never explicitly states when to use it, preconditions, or names an alternative tool an agent should pick instead.

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

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

With no annotations, the description carries the full burden. It does disclose two useful traits: the evaluation is rule-based (deterministic, not probabilistic) and it does not access chat histories. However, it says nothing about side effects, permissions, cost, or what the caller receives back, which is a large gap for an unannotated tool with no output schema.

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?

Two short sentences with the core characterization front-loaded and no padding. It is efficient, though the brevity is achieved partly by omitting information rather than by compression.

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 9-parameter tool with no annotations, no output schema, and no parameter descriptions, the definition is far short of what an agent needs to invoke it correctly. The description establishes framing but nothing about required inputs (goal, acceptance), field meaning, or return behavior.

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?

Nine parameters with 0% schema description coverage and no annotations; the schema gives only types (booleans like cancelled, acceptancePassed, artifactCreated, permissionRequired, an integer repeatFailures, and free-text strings). The description explains none of them, leaving semantics such as what 'acceptance' must contain entirely undocumented.

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 characterizes the tool as a 'rule-based preflight for an explicit task state,' which conveys the general shape of the operation but never states a concrete verb or outcome (validate, score, gate?). The negative clauses distinguish it from tools that read chat history or predict probabilities, but those are not the listed sibling, so no real sibling differentiation occurs.

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?

Only negative scope is given ('does not read chat histories or predict a calibrated success probability'). There is no statement of when to call this versus alternatives, nor any precondition such as 'call before marking a task complete' that would let an agent place it in a workflow.

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