Firstmise: One contact for your kitchen opening service gaps

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered without the description. The description does add a content hint beyond the annotations by signaling that the payload explains what happens to a request and enumerates the request fields, but it says nothing about response format, size, or how stable the content is.

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 with no filler, and the three content areas are enumerated compactly. It is a sentence fragment that omits the operative verb ('returns'/'describes'), which slightly weakens front-loading but adds no padding.

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 parameters and no output schema, the description is the only place an agent can learn what comes back, and it only gestures at the return content in three vague clauses. For a zero-argument documentation tool it is minimally sufficient, but it never states that the result should be read before calling submit_request, which is the main thing an agent needs.

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 there is no parameter semantics for the description to carry and the baseline of 4 applies. The mention of 'request fields' is content the tool returns, not an input contract, so it neither helps nor hurts here.

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 reads as a list of topics ("what Firstmise does, what happens to a request, and the request fields") rather than a stated verb+resource, so the agent must lean on the name describe_business and the title 'About Firstmise' to infer that this returns documentation. It never contrasts itself with the sibling submit_request, so the boundary between learning about the business and filing a request is left implicit.

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 when-to-use guidance at all: nothing says to call this before submit_request to learn the required fields, which is the obvious workflow given the sibling. No exclusions or alternatives are mentioned, leaving the agent to guess its place in the sequence.

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?

Annotations only give hint flags (not read-only, not destructive, not idempotent, closed-world); the description goes well beyond them by disclosing that a reference number is issued, that a human review of equipment/arrangements/questions occurs, that a reply arrives by email, and that contact data is retained separately for 24 months and deletable on request. The only blemish is the duplicated 'reference number' claim, which wastes space rather than misleading.

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 core fact is front-loaded, but 'It is kept with a reference number' is immediately restated as 'Your request is recorded with a reference number,' and the retention sentence is long and legalistic. The content is dense with useful facts but the redundancy and run-on phrasing cost it a point.

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 non-idempotent submission tool with 8 parameters, no output schema and undescribed schema fields, the description does well on process and data retention but leaves the parameter layer almost entirely undocumented. An agent can understand the consequences of calling it, but not how to populate most of the payload.

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, several nested, so the description must carry the burden — and it does not. It obliquely gestures at 'reported equipment, existing arrangements and remaining questions' and mentions leaving an email address, but the action enum (buy/source/quote/lease/license...), budget, quantity, timing and geography fields are entirely unexplained, leaving an agent to guess at their intent.

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 names a concrete action and destination — 'Send a requirement to Firstmise' — and explains the outcome: it is recorded with a reference number and Firstmise replies by email with a proposed schedule and nonbinding estimate. That is specific enough to know what the tool does, though it never distinguishes this from the sibling describe_business tool.

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 exclusions are useful: 'This request books no visits' and 'Nothing is ordered or committed until you agree terms' tell the agent this is a non-binding intake step. However, there is no positive guidance on when an agent should call this versus describe_business, and no prerequisites or conditions of use are stated.

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