Formspree MCP by usefulapi

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely new behavioral context — that results come from a 100-submission sample and that no submission values are returned. It also discloses the underlying request shape. It does not mention what happens with an empty or brand-new form, which is the main remaining behavioral unknown.

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?

Three short sentences, front-loaded with the return content, then the usage hint, then the endpoint. Every sentence carries distinct information — what, when, and how — with no restatement of the title or annotations.

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, read-only lookup with no output schema, the description supplies exactly the missing pieces: output shape (names only, not values), sampling scope (latest 100 submissions), and purpose in a larger workflow. An agent can call this correctly and interpret the result without further documentation.

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 the parameter_semantics baseline is 4. The closing GET path is informative context rather than a parameter contract, and it notably references a {hashid} that has no corresponding schema property — but that ambiguity exists in the schema, not in the description's handling of 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?

The description names a specific resource (the field names/columns of a form's submissions) and a specific derivation method (latest 100 submissions), then explicitly states what is not returned ("Returns names only, no submission data"). This separates it cleanly from formspree_list_submissions and formspree_list_spam_submissions, which return actual submission rows.

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?

"Use it to pick the columns for formspree_list_submissions" gives an explicit, actionable when-to-use condition and names the downstream sibling it pairs with. It stops short of stating exclusions or prerequisites (e.g. that the form must already have submissions, or when the other sibling should be preferred), so it is not a full when/when-not treatment.

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 already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description adds the underlying GET path and the fact that results include both auto-flagged and owner-marked spam, which is genuinely useful provenance, but it doesn't discuss paging behavior or response shape beyond the default sort.

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?

Three short sentences, front-loaded with scope, then the use case, then the equivalence to the sibling. No filler and nothing repeated verbatim from the schema.

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 read-only, annotated, fully described 6-param list tool with no output schema, the description covers what the tool returns (spam-flagged or owner-marked submissions, newest first) and how paging mirrors the sibling. Only the response envelope is left implicit, and the schema notes about next_offset and _status partially cover that.

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 100%, with limit, order, since, offset, columns, and include_delivery_status all documented in-schema. The description only adds a cross-reference ("same filters and paging as formspree_list_submissions") and the spam=true endpoint, adding no syntax or semantics beyond the schema.

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 ("List the submissions") scoped precisely to spam (flagged by Formspree or owner-marked), plus default ordering. It explicitly contrasts itself with formspree_list_submissions, so an agent can tell the two apart without opening a schema.

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?

"Use it to check for false positives" gives a concrete context, and the pointer to formspree_list_submissions for the same filters implies the non-spam alternative. It stops short of an explicit "do not use for X" exclusion, so it's clear but not fully routing.

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 already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely new context: default newest-first ordering, the personal-data exposure warning, and the offset/next_offset paging model.

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?

Three tight sentences plus an endpoint line; the scope and default ordering are front-loaded, and the privacy warning sits next to the columns advice where it is actionable. No filler.

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 read-only list tool with full schema coverage and annotations, the description covers defaults, filtering, paging, field selection and data-sensitivity. No output schema exists, yet the shape of a submission ('_date and one value per form field') is described, leaving nothing an agent needs missing.

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 100%, so baseline would be 3, but the description adds meaning beyond the schema by explaining when to use 'columns' (privacy-driven minimisation) and the default sort direction. It does not restate limit/offset mechanics, which the schema already documents.

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 resource (the form's submissions) with an explicit scope note '(not spam)' that separates it from formspree_list_spam_submissions, and names the default ordering. No schema inspection is needed to know what it returns.

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?

Gives concrete guidance for filtering ('Filter by date with since') and paging ('page with limit and offset'), and a conditional recommendation ('ask for the columns you need'). It implies the spam sibling via '(not spam)' but never names it explicitly as an alternative, keeping this at a 4.

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