closelook-intelligence

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

With no annotations, the description carries the full burden. It implicitly discloses this is a read-only reporting tool ('fastest read', 'side-by-side') and adds temporal context (end-of-day). It doesn't mention permissions or side effects, but for a non-mutating comparison tool, this is sufficient.

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 core purpose, followed by a usage-oriented closing. Every word earns its place; no redundant or vague language.

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 tool with no output schema, the description fully covers what data is returned (specific indices and metrics), the time horizon (end-of-day), and the intended use case. No substantial 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?

The tool has zero parameters, so schema coverage trivially covers everything. The description adds value by explaining what the output includes (last close, 1-day, 1-week, MTD returns), which is more useful than parameter syntax. Baseline is 4 for zero-param tools.

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 opens with 'Side-by-side of all Closelook headline indices' which clearly defines the tool's function (comparing indices) and resource (all listed indices). It lists specific index names and metrics, distinguishing it from sibling tools like get_index_snapshot, which likely focuses on a single index.

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 clear use context: 'The fastest read on where the AI trade rotated, end-of-day.' This implies when to use (quick high-level overview) but doesn't explicitly mention alternatives or exclusion criteria. It's a clear context signal without full comparison 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 full burden. It adds useful context about the glossary's size and categories, including examples like 'Numerator Regime.' However, it does not disclose the return format or behavior for unknown terms, which would be valuable for a simple lookup 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 a single, well-structured sentence. It front-loads the action ('Get... definition') and efficiently packs relevant scope details (260+ glossary entries, term categories, coined concepts) without any filler or repetition.

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 one-parameter glossary lookup with no output schema and no annotations, the description is mostly sufficient. It clearly defines the input and the tool's scope, but lacks a note on return value or error behavior, which would make it fully 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?

The schema already describes the only parameter 'term' with examples. The description adds extra examples and category context but does not add meaningful syntax or boundary details. With 100% schema description coverage, a baseline score 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 clearly states the tool's function: 'Get Closelook’s definition of a financial or market term from its 260+ entry glossary.' It is specific with a verb and resource, and the glossary scope (classic finance, chart indicators, etc.) distinguishes it from sibling tools like compare_indices or search_closelook.

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 clear context for when to use this tool: when you need a definition of a term from Closelook's glossary. It does not explicitly mention exclusions or alternatives, but the scope and sibling tool names make the intended use clear.

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 must convey behavior on its own. It states that it 'Returns level, recent returns and the strongest/weakest sub-indices, end-of-day,' which discloses the output and timing. However, it does not explicitly state that it is read-only or mention any rate limits or side effects, leaving some burden unaddressed.

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 only two sentences and immediately identifies the tool's purpose and output. It packs useful information about indices, return fields, and timing without any fluff.

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 tool's simplicity (one parameter, no output schema), the description covers the main return components (level, returns, sub-indices). It does not specify the exact time frame for 'recent returns,' but overall it is sufficient for an agent to invoke correctly.

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 only describes the parameter as 'Index code' with an enum. The description expands each enum value with parenthetical meanings (e.g., 'RUBIN (AI buildout)'), giving the agent clear semantic understanding of what each index represents. This significantly exceeds the schema's minimal 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 clearly states 'Current snapshot of one proprietary Closelook index' and enumerates the specific indices, plus returns level, recent returns, and sub-indices. This distinguishes it from sibling tools like compare_indices, which suggests comparison, while this tool focuses on a single index.

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 when-to-use guidance or mention of alternatives. However, the phrase 'one proprietary Closelook index' implies it's for retrieving a single index snapshot, in contrast to sibling tools. Usage is only implied, not formally 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 carries the disclosure burden. It provides useful transparency by specifying exactly what is returned (headline, core statement, link for two components), but it does not explicitly state read-only behavior, error handling, or what happens if no view exists.

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, front-loaded sentence that names the resource, lists the components, and specifies the output fields. Every word contributes to understanding, with no redundancy or 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?

Given the zero-parameter schema and lack of output schema, the description does most of the work by enumerating the exact return content. It could be stronger by clarifying whether both components are always present or how 'latest' vs 'today's' is resolved, but it is largely sufficient for a simple getter.

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 there is no parameter semantics to add. The baseline of 4 applies because no parameters need explanation.

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 explicitly names the resource ('Closelook's latest published market view') and breaks it into two concrete outputs (Morning 10 and Daily Pulse thesis), making the tool's purpose immediately clear. This distinguishes it from sibling tools like compare_indices or search_closelook, which serve different functions.

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 a use case: retrieving the latest published market view. However, it does not explicitly state when to use this tool over alternatives like search_closelook or get_index_snapshot, nor does it provide any 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, the description carries the full burden. It discloses the output behavior: returns matching pieces with a one-line summary and link. This goes beyond a simple 'search' and gives the agent expectations for results. It does not cover pagination, result limits, or auth requirements, but for a search tool this is reasonably transparent. However, it could mention sorting or result count, so not a 5.

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 two sentences, front-loaded with the action and scope, and ends with a usage tip. Every sentence earns its place. No redundancy or wasted words.

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?

The tool is relatively simple with only 2 parameters, no output schema, and no annotations. The description covers the search scope, return format, and usage context. It could mention the default of searching all types, but that is implied by the 'type' parameter default. It is complete enough for an agent to use effectively.

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 both parameters having descriptions. The 'type' parameter has an enum with descriptions, and 'query' has an example. The tool description itself does not add additional parameter semantics beyond the schema, so it earns the baseline score for high schema coverage.

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 function: searching Closelook's research corpus across multiple content types. It specifies the verb (search), the resource (research corpus), and the scope (101 explainers, glossary, heresies, reports, strategy notes, finance library). It also mentions the return format, distinguishing it from sibling tools like define_term which likely handles glossary definitions specifically.

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 explicit usage guidance: 'Use for "what has Closelook written about X"'. This tells the agent when to invoke this tool. It does not explicitly mention alternatives or when not to use it, but the clear use case is sufficient context. Sibling tools are not referenced, but the guidance is clear enough for an AI agent.

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