Thales

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

With no annotations, the description carries the full burden. It discloses that all series are indexed to 100 at inception, that paper capital is arbitrary, and that all figures are simulated paper trading. It also notes the limit of 20 most recent orders, adding useful behavioral context beyond the obvious summary functionality.

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 three sentences, each serving a purpose: listing content, clarifying the indexing/normalization, and emphasizing the simulated nature. There is no redundancy, and the most important information (what the tool summarizes) is front-loaded.

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, no-output-schema tool, the description covers the key content (returns, drawdown, live days, orders) and important caveats (simulated, indexed). It could be marginally improved by specifying units or return format, but the provided details are sufficient for an agent to understand the tool's scope.

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 has zero parameters, so the baseline is 4. The description does not need to explain parameters, and the schema is trivially complete. No additional parameter meaning is required.

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 clearly states the tool provides a summary of every strategy sleeve, listing specific metrics (returns, drawdown, live days, orders). Although it lacks an explicit verb like 'get' or 'list', the resource and scope are unambiguous, distinguishing it from sibling tools like sleeve_record which likely targets a single sleeve.

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 explains what the tool returns but provides no guidance on when to choose this over siblings. There is no explicit 'use this when...' statement, no mention of alternatives, and no exclusions. The only contextual hint is 'fleet_overview' implying a fleet-wide scope, but this is inferred rather than stated.

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 adds useful behavioral context: criteria are frozen on a specific date, and the gate tests operational competence, not alpha. This provides a clear purpose and boundaries beyond a generic status check.

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 a single, well-structured sentence that packs essential information: what the gate is, criteria frozen date, what it reports, and a key interpretation note. No filler or redundancy.

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 status tool with no output schema, the description explains the nature and scope of the gate. It could be more precise about the output fields, but it sufficiently informs an agent of the tool's purpose and constraints.

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 parameters, so schema coverage is 100%. Baseline for 0 parameters is 4; the description does not need to add parameter info, and it doesn't, but the context of the tool is well conveyed.

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 clearly states the tool provides status for a pre-registered go-live gate, specifying frozen criteria, current progress, and interpretation. It uniquely identifies the resource, distinguishing it from siblings like fleet_overview or kill_list.

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 explicit guidance on when to use this tool versus alternatives, but the context implies it is the go-to for gate status. The lack of sibling overlap reduces the need for exclusions.

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 provided, the description carries full behavioral burden. It only describes content (rejected ideas) and does not disclose side effects, permissions, or whether the operation is read-only. Minimal transparency beyond data nature.

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?

Extremely concise: two sentences that front-load the core purpose and add a unique value proposition ('credibility mechanism'). Every sentence earns its place with no verbosity.

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 parameterless list tool without output schema, the description adequately explains what the tool returns. It lacks mention of ordering, filtering, or pagination, but is likely sufficient for basic use. Slightly incomplete given no contextual cues relative to siblings.

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 has zero parameters with 100% schema coverage (empty schema). The description adds no parameter details, which is acceptable as there are none to describe. Baseline for 0 params 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 clearly states the tool provides a list of rejected strategy ideas with dates, verdicts, and reasons. It distinguishes from sibling tools like 'fleet_overview' or 'gate_status' by focusing on failures as a credibility mechanism.

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 guidance on when to use this tool versus alternatives. The description does not mention context, prerequisites, or exclusions, leaving the agent to infer usage from the content 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that documents are auto-published verbatim by a daily export, and mentions that verdicts include nulls, which is useful context. However, it stops short of describing the format or contents of the manifest itself.

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 concise and front-loaded. It explains what the tool returns, provides context about the data source, and points to an alternative in just two sentences. Every clause adds value.

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 tool with no output schema, the description adequately conveys the tool's purpose and return value. It names the manifest and points to research_note for individual documents. It could be slightly more explicit about what the manifest contains, but the listed document types give a good sense.

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, and the schema is empty. Per the baseline for zero-parameter tools, this scores a 4. The description does not need to explain parameters, and it correctly focuses on the return value.

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 clearly states the tool's purpose: it returns the manifest of all internal research documents. It lists specific types of documents (experiment pre-registrations, incident write-ups, verdicts) and distinguishes itself from the sibling tool research_note, which fetches individual documents.

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 directly instructs the user to use research_note to fetch a document, implying this tool is for obtaining the manifest/list. This explicit alternative differentiation provides clear usage guidance.

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 the transparency burden. It discloses that content is verbatim internal writing, that credential identifiers are redacted, and that the output is full markdown text. It could add detail about behavior on invalid slugs or availability, but the key behavioral traits are covered.

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 concise sentences with no filler. The first sentence front-loads the action and the source of the identifier, and the second clarifies the nature of the content and redaction. Every word 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?

Despite having no output schema, the description is adequate for a one-parameter fetch tool: it specifies the content type (full markdown text), the source of the slug, the verbatim nature, and the redaction caveat. Missing details like error handling on invalid slugs are minor and would not impede correct invocation.

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 already fully describes the single required parameter 'slug' with an example, so schema coverage is 100%. The description adds the meaningful constraint that the slug must come from research_journal, which is useful, but it does not add syntactic or format details beyond what the schema provides. Baseline 3 is appropriate.

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 action: retrieving the full markdown text of one published research document by slug. It explicitly points to research_journal for the list, thereby distinguishing itself from sibling tools like research_journal (which lists) and other retrieval tools.

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 clearly implies the prerequisite workflow: first consult research_journal to obtain a valid slug, then call this tool with that slug. It does not enumerate exclusions or alternatives, but for a simple single-resource fetch this is sufficient 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not state that the tool is read-only, safe, or idempotent. The content is implied but no details on side effects, auth requirements, or output format are given.

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 a single sentence, which is concise. However, it reads as a list of topics rather than a clear statement of functionality, reducing its effectiveness slightly.

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?

Given no parameters and no output schema, the description should fully explain what the tool returns. It lists three topics but does not clarify if the output is a concatenated string, a structured document, or multiple calls. This is incomplete for a zero-input tool.

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 parameters and schema description coverage is 100% trivially. The description does not add parameter meaning beyond the schema, but since there are no parameters, a baseline of 3 is appropriate.

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 lists topics ('What Thales is, every machine-readable endpoint, and the verification standard') but does not use a clear verb or specify the action of the tool. The name 'site_guide' suggests an informational role, but the purpose remains vague without stating whether it returns documentation, metadata, or a summary.

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 provides no guidance on when to use this tool versus siblings like 'fleet_overview' or 'gate_status'. There are no use-case indications, prerequisites, or exclusions, leaving the agent to infer usage from the tool name 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?

With no annotations, the description carries the full burden. It discloses that figures are simulated paper trading, which is useful context, and implies a public read operation. However, it doesn't mention rate limits, error behavior, or explicit safety guarantees, leaving gaps.

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, front-loaded with the tool's purpose and contents, followed by a critical simulation warning. Every word earns its place with no fluff or redundancy.

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?

Given the simple parameter set and no output schema, the description adequately covers the tool's return contents and simulation context. It could elaborate on the return format or pagination, but for a list/record fetch, it is reasonably complete.

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%, providing baseline 3. The description adds value by explaining the indexed performance curve (100 = inception) and enumerating the include options, which goes beyond the schema's terse descriptions.

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 clearly states the tool returns the full public record for one sleeve, listing specific components (stats, indexed performance curve, drawdown series, order log). It does not explicitly differentiate from siblings, but the resource and action are clear.

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 usage (fetch a sleeve's record) but provides no explicit when-to-use guidance or alternatives among siblings. It doesn't state exclusions or conditions, so only implied context exists.

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