ProjectPermit

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

With no annotations provided, the description carries the full disclosure burden, and it does reveal meaningful traits beyond the schema: evidence-linked determinations, deterministic identity, duplicate-suppression idempotency, and a mutation gate. Yet 'mutation gate' is never explained, and the side-effect profile is unclear (e.g., what resolve_address triggers or whether the tool persists anything), so the behavioral picture remains incomplete.

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?

Four short sentences with the usage context front-loaded and zero filler; every sentence earns its place. The output list, however, is dense jargon ('deterministic identity, duplicate-suppression idempotency, mutation gate') that slightly hampers readability, keeping it from a perfect 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?

An output schema exists and the complex inputs are largely self-documenting, so the lack of return-format detail is not a liability. But for a tool with this much surface area, there is no routing guidance between single vs. batch variants, no mention of when projectpermit_info is the right call, and no disclosure of resolve_address side effects — leaving an agent to guess at the edges.

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 high (83%), which sets a baseline of 3, and the description adds genuine parameter-level guidance: family+action as the mandatory starting point, a known-facts-only policy to avoid guessing, and the role of context.prior_decision_identity for repeat checks. That is real value beyond the per-field 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 identifies a specific purpose — evaluating proposed work before quoting/scheduling — and names the resource (project requirements) with an inventory of what it returns. It is clear about the tool's job, but it never differentiates itself from the sibling check_project_requirements_batch or projectpermit_info, so it falls short of a 5 on the sibling-distinction bar.

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?

It explicitly scopes when to use the tool ('Use for proposed work before quoting/scheduling') and gives entry guidance ('Start project with family + action and add only known facts'), plus a concrete repeat-check instruction via context.prior_decision_identity. However, it names no alternatives or when-not-to-use exclusions, leaving the choice versus the batch sibling implicit.

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 behavioral burden. It usefully discloses that malformed items remain isolated as per-item failures, which is important for a batch API. However, it does not state whether evaluation is read-only, how partial success is represented, or other failure/rate-limit behaviors.

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 two sentences with no filler. It front-loads the batch capacity and core purpose, then compactly states the per-item shape and the failure-isolation behavior. Every clause earns its place.

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 batch tool, the description covers capacity, per-item input structure, and malformed-item handling, and an output schema exists to detail return values. It is slightly incomplete because it never points the agent to the single-project sibling or clarifies when batch is the wrong choice.

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. It does by highlighting the meaningful item fields: jurisdiction, project.family/action, optional property/address/context, and client_ref. This gives an agent a concrete starting point for constructing items, while the schema supplies detailed field semantics.

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 opens with a specific action and resource: 'Evaluate 1-50 normalized projects in one call.' It clearly conveys this is a batch evaluation tool and summarizes the per-item inputs. It does not explicitly contrast itself with the sibling check_project_requirements, so it stops short of a 5.

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 '1-50 ... in one call' phrasing implies this tool is for multi-project evaluations, and the sibling name suggests check_project_requirements is the single-item alternative. However, the description never explicitly states when to use the batch tool versus the singular sibling or when the batch variant is inappropriate.

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 full responsibility. It discloses that the tool only performs capability discovery and does not evaluate permits, which sets accurate expectations. It also surfaces that the tool returns idempotency and safe-writeback semantics, adding behavioral context about subsequent write operations.

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 'Use first' directive. No filler; every phrase adds distinct information about timing, content, or scope.

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 no-parameter capability-discovery tool with an output schema, the description covers what the tool does, what it returns, and what it does not do. The only omission is naming the sibling tools for permit checks, but the sibling list is available in context.

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 input schema has zero properties, so the description has no parameter burden. The baseline for zero-parameter tools is 4, and the description appropriately focuses on output content and usage rather than parameters.

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 action ('Use first to get') and a concrete resource list (supported Canadian cities/families, identity/idempotency, safe-writeback semantics). Explicitly distinguishes itself from permit-checking siblings by declaring 'no permit determination is performed.' An agent can immediately tell this is the capability-discovery tool, not the requirement checker.

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?

Opens with the directive 'Use first,' which tells the agent the intended call order relative to other tools. 'Capability discovery only; no permit determination is performed' clearly marks when not to use it, and the sibling names make the alternative obvious. It could have named the sibling tools explicitly, but the context is unambiguous.

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