SignalForge AI SFConnect

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

The readOnlyHint=true and openWorldHint=false annotations already establish that this is a safe, closed read. The description adds useful context about the returned payload—connected, version, cloud, labels—but omits whether it returns all accounts, ordering, empty-state behavior, or auth requirements.

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 compact sentence fragment front-loads the main resource and payload fields without filler. The lack of a verb makes it slightly less clear than a complete sentence, but nothing is wasted.

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 tool with annotations covering safety, the description gives the key returned fields. However, it is still thin: it does not state that it lists accounts, how labels are represented, or how it differs from ea_status, and no output schema exists to fill those gaps.

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?

There are zero input parameters, so there is no parameter semantics to clarify. The baseline for a no-parameter tool is 4.

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 the resource (MT5 accounts) and the fields bundled with it (EA state, labels), but it is a noun phrase without an action verb. It also does not distinguish this endpoint from the sibling ea_status tool, which likewise surfaces EA state.

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 is provided. It does not explain whether to call this for account inventory versus ea_status for EA-specific status, leaving the choice 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data. The description adds the return content (version, connected, last ping), which is useful since there is no output schema, but says nothing about freshness, scope, or what 'connected: false' implies.

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 the resource front-loaded and the returned fields listed in order; no filler, no redundancy. Everything present 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?

With no output schema, the description must carry return-value burden, and it does list the key fields. However, it is ambiguous whether this returns one EA status or a status for every account (the 'per account' phrasing with zero parameters implies all accounts but never says so), and it omits any note on data freshness or aggregation.

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 beyond what the empty schema already shows. Baseline of 4 applies.

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 (EA status per account) and enumerates the fields returned (version, connected, last ping), so an agent knows what data it gets. It lacks an explicit verb and never differentiates itself from siblings like accounts or me, and the acronym 'EA' is never expanded.

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 statement of when to call this versus the sibling tools (accounts, me, recent_signals), and no prerequisites or exclusions. An agent must infer that this is the health/connectivity check tool from the returned field names alone.

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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description does add one genuine behavioral detail beyond that — the email is returned masked, a privacy trait the agent would not otherwise know — but says nothing about response shape or freshness of the account dates.

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 short sentence front-loads the resource and then lists the returned fields; nothing is padded or redundant. The fragment style is slightly terse but costs no comprehension.

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 parameters, the description carries the load of telling the agent what comes back, and it does so by naming the four fields. The only gap is that it does not clarify the boundary with the 'accounts' sibling, which matters in this family of tools.

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 per baseline there is no parameter semantics burden to discharge. The description correctly implies a no-argument call by framing the result as the caller's own identity.

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 the resource precisely as the caller's own SignalForge user record and enumerates the returned fields (id, plan, masked email, account dates). It is clear what the tool does, but it does not contrast with the sibling 'accounts', which an agent could plausibly confuse with fetching user/account profile data.

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?

Usage is only implied: 'Your ... user' suggests it returns the authenticated caller's identity rather than a list of accounts, which is a soft disambiguation from the 'accounts' sibling. There is no explicit statement of when to call this instead of 'accounts' or any prerequisite context.

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 cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description's job is smaller. It still adds real behavioral context: results are ordered newest first, scoped to the caller's own signals, and the text fields originate from alerts and must be treated as untrusted data — a security-relevant disclosure not present in any structured field.

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 sentences, zero filler, with the ordering and scope constraint front-loaded before the untrusted-data warning. Every clause carries information an agent needs.

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 simple three-param read tool with full schema coverage, annotations for safety, and no output schema, the description covers scope, ordering, and the nature of returned text fields. Only minor gaps remain, such as what a signal record contains structurally or how pagination beyond limit behaves.

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 100%, so limit, since, and account_id are already fully documented in the schema. The description adds no filtering syntax, default behavior, or paging semantics beyond that, so baseline 3 applies.

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+resource: 'Your signal history, newest first', with a scope qualifier ('only your own signals'). This is clearly distinguishable from send_signal and signal_detail, though it never names signal_detail as the single-record alternative.

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?

Usage is implied rather than stated: the agent can infer this is the list-my-history tool. There is no explicit when-to-use versus signal_detail or accounts, and no stated prerequisites.

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?

Beyond the minimal annotations, the description discloses the dry-run preview behavior, live auth scope requirements, plan prerequisite, server-side validation, a 10/min rate cap, and 24-hour idempotency duplicate semantics. It also clarifies the destructive scope of closebuy/closesell, which is exactly the kind of behavioral context an agent needs before invoking a trading tool.

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 dense and front-loads the core purpose before moving into operational constraints. It is efficient and mostly earns its length, but the single-paragraph form makes several independent rules harder to scan than they could be.

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 28-parameter mutation tool with no output schema and partial schema coverage, the description covers operational safety and key side effects well. It does not fully explain the action enum, many numeric parameters, or what a successful response contains beyond the duplicate indicator, so it remains incomplete for the tool's complexity.

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 description adds important meaning for dry_run, lot, idempotency_key, close aliases, and symbol/action validation. However, with 28 parameters and only 54% schema description coverage, many parameters such as tp1–tp5, trailing, breakeven, entry_pct, and entry_pips, as well as most action enum values, remain unexplained by either the schema or the description.

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 states a specific verb and resource: submit a trading signal to YOUR EA. That clearly separates it from read-oriented siblings such as accounts, ea_status, recent_signals, and signal_detail, though it does not explicitly name those siblings.

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 gives explicit operating conditions: dry_run=true previews only, live sending needs a trade-scoped key, and a trading plan is required. It also explains when to use idempotency_key and when to prefer close with side over closebuy/closesell, though most other action choices are not similarly explained.

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?

Beyond the readOnlyHint annotation, the description discloses that access is restricted to the caller's own signals and that unauthorized ids return not_found without revealing existence — a meaningful security behavior an agent must know. It also warns that text fields are untrusted alert data, mitigating prompt injection, though it says nothing about the returned record's shape.

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, each carrying distinct information: scope, authorization/error behavior, and data-trust warning. It is telegraphic in places ('One signal by id') but front-loaded and free of 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?

With no output schema, the description should hint at what a signal record contains; instead it only mentions untyped 'text fields' from alerts. Access control and error semantics are well covered, but the return payload is left opaque for a tool whose whole job is returning a record.

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 0% description coverage, and the description only restates that lookup is 'by id' without explaining the integer's origin, format, or whether it comes from recent_signals. It adds marginal meaning over the schema's bare "id: integer".

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?

"One signal by id" states a specific resource and scope, making clear this is a single-record fetch rather than a listing. It implicitly contrasts with the listing sibling recent_signals, though it never names that sibling to make the distinction explicit.

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 single-record framing implies when to use this over a listing tool, and the ownership constraint ('only your own signals') is stated. However, no sibling is named and there is no explicit when-not-to-use guidance, so the routing 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.