Loop Desk

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

With no annotations, the description carries the full burden. It usefully discloses that lookups are scoped to the calling API key, which is real behavioral context an agent can't infer from the schema, but it says nothing about behavior when the id is missing, unknown, or owned by another key.

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 short sentence, front-loaded with the verb and resource, no filler. It is arguably too terse, but the terseness is a completeness problem rather than a structural one.

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?

A simple single-parameter read tool with no output schema needs little, and the scoping note helps. Still missing are the id format and the not-found/unauthorized behavior, which an agent would want before calling.

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 0%, so the description should compensate for the single 'id' parameter. It only says 'by id' and reveals nothing about the identifier's format or constraints, leaving the agent to guess at what a valid id looks like.

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 and resource ('Fetch one loop by id'), which clearly separates it from the siblings list_due (enumeration) and register_loop (creation). It doesn't name the siblings, but the single-item fetch intent is unmistakable.

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?

No when-to-use or when-not-to-use guidance, and no mention of list_due as the alternative for discovery. The phrase 'for the calling API key' hints at a scoping constraint but doesn't tell the agent when this tool is the right choice.

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses the 'open loops' scope (presumably excluding closed ones) but says nothing about ordering, pagination, result limits, or whether this is strictly read-only — gaps that matter for a list endpoint with zero annotation coverage.

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 sentence, no waste, and the filter condition is stated immediately after the resource. Nothing could be removed without losing information.

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?

With no output schema and no annotations, the description should say at minimum what a returned loop looks like or whether results are ordered/limited, and what the no-`before` default is. For a single-parameter read tool the gap is modest but real.

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 0% — the schema only declares `before` as an untyped-format string. The description supplies both the format (ISO datetime) and the inclusivity semantics ('on or before'), which is exactly the value the schema lacks.

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?

Specific verb (List) plus resource (open loops) plus a filter condition (due on or before `before`). It is clearly distinguishable from the siblings get_loop (single fetch) and register_loop (create), 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?

The filter clause implies the use case (finding loops by due date), but there is no explicit when-to-use, no mention of alternatives, and no statement about what happens when `before` is omitted — the one parameter is optional, so the default behavior is left to inference.

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 and mostly fails: it doesn't say whether registration is idempotent, how external_ref or deadline_desk_receipt_id affect deduplication, or whether the loop can later be modified. 'Returns TRACE receipt' is the only behavioral disclosure, and it is unexpanded.

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, front-loaded with the action and the valid kinds. Nothing is wasted, but the brevity comes at the cost of specification rather than being achieved alongside it.

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?

A 9-parameter mutation tool with no annotations, no output schema, and 11% schema coverage needs substantially more description than two sentences. The undeclared TRACE receipt format and undocumented optional parameters leave real gaps for correct invocation.

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 11% (only due_at), and 9 parameters exist, yet the description only restates the kind enum that is already in the schema. Counterparty, amount_cents, currency, source_url, external_ref, notes, and deadline_desk_receipt_id are left with no explanation anywhere.

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 (Register) and resource (open loop) and enumerates the valid kinds, so the agent knows this is a creation tool for tracked obligations. It doesn't explicitly contrast with siblings get_loop and list_due, but the verb alone is enough to separate creation from retrieval.

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?

No statement of when to use this versus list_due/get_loop, no prerequisites, and no guidance on what makes something an 'open loop' worth registering. The agent must infer usage entirely from the name.

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