Washington State Clean Buildings compliance scope and indicative fee requests
Scored across 2 tools
The two tools split cleanly into an informational tool (describe_business) and a write action (submit_request), so misselection is unlikely. The only mild blur is that submit_request's long description also explains the process and request fields, overlapping with what describe_business ostensibly covers.
Both names use a consistent verb_noun snake_case pattern (describe_business, submit_request). The verbs accurately signal read-only versus write behavior.
Two tools is thin for a compliance workflow server; there is no status lookup, listing, or evidence submission despite the process description implying those steps. It is defensible as a minimal intake surface but sits at the borderline of under-scoped.
The surface is one-directional: an agent can describe the service and submit a request, but cannot retrieve a request by its reference number, check status, or supply the applicability evidence the description repeatedly references. This creates a dead end after submission.
What Tendmark Buildings does, what happens to a request, and the request fields.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without the description. The description adds that the tool surfaces business purpose, request lifecycle, and field documentation — useful content context, though it does not say whether the answer is static text or fetched from a live config, which matters since the hint says closed-world.
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?
A single compact sentence with no wasted wording, and the subject ('what Tendmark Buildings does') is front-loaded. It is a sentence fragment without a main verb, which slightly blunts the opening but costs no real clarity.
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 reference tool with no output schema, the description should convey the shape of what comes back; it lists topics covered but not the form (prose overview vs structured field list). What it does say is sufficient to know the domain of the answer, but an agent cannot predict whether it will get free text or field-level detail.
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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The mention of 'request fields' is not a parameter of this tool — it refers to sibling submit_request's inputs — so it adds context but no parameter 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 enumerates content topics ('what Tendmark Buildings does, what happens to a request, the request fields') rather than stating a verb+resource like 'return reference documentation.' It reads as a noun-phrase table of contents, so an agent can infer it is an informational lookup distinct from the action-oriented sibling submit_request, but only by inference.
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?
There is no explicit when-to-use statement, no prerequisite, and no mention of the sibling submit_request. The phrase 'what happens to a request' hints it is meant to be read before submitting, but the agent must supply that routing logic itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a requirement to Tendmark Buildings. It is kept with a reference number. Your request is recorded with a reference number. Tendmark will review applicability evidence and existing work, establish data access needs, arrange qualified-role and implementation responsibilities, and develop a building-specific scope and indicative fee. We reply by email when you leave an address, carrying forward this brief and its open questions. Nothing is ordered or committed until you agree terms. Contact details are kept apart from the requirement, while we correspond or do business and for 24 months after, so a later request picks up where it left off; ask us to delete them at any time.
| Name | Required | Description | Default |
|---|---|---|---|
| need | Yes | ||
| action | No | ||
| budget | No | ||
| timing | No | ||
| contact | No | ||
| quantity | No | ||
| geography | No | ||
| specifications | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the safety profile (non-read-only, non-idempotent, non-destructive). The description adds real behavior: a reference number is returned, Tendmark reviews and responds by email, contact details are stored separately for 24 months with a deletion right, and no order is placed until terms are agreed. That is substantive context beyond the annotations.
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 opening is front-loaded and the commitment/retention notes are valuable, but the second sentence ('It is kept with a reference number. Your request is recorded with a reference number.') is a redundant restatement that wastes space. The middle sentence listing internal review workflow is long and only marginally relevant to the caller.
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 an 8-parameter, nested-object, non-idempotent write tool with no output schema and 0% schema coverage, the description should clarify how the structured inputs (action, budget, quantity, timing, geography, specifications) shape the submission. It focuses instead on downstream process and data retention, leaving the calling contract under-explained.
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% across 8 parameters with nested objects, so the description must carry the load — but it only obliquely touches contact ('when you leave an address') and the brief itself. It never explains need, action enum, budget, timing, quantity, geography, or specifications, leaving most inputs 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?
States a specific verb (send) and resource (a requirement to Tendmark Buildings), which is clearly a submission action distinct from the sibling describe_business. It doesn't explicitly name or contrast with the sibling, keeping it 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 description implies the context (submitting a requirement to get a scope and indicative fee) and clarifies nothing is committed until terms are agreed, which helps an agent decide to call it. However, there is no explicit when-to-use/when-not guidance or any routing against describe_business.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
describe_businesssubmit_requestWA permit rules (city + state baseline, cited), parcel zoning, L&I checks, Seattle estimates & ROI
EV-charging site analytics: utilization, demand, peak saturation and corridor benchmarks.
EV-charging site analytics: utilization, demand, peak saturation and corridor benchmarks.
Auditable US clean-energy tax-credit scenarios for 45Q, 45V, 45Y, 48E, and 45X.
Add one secure layer between your agents and this server.