Tapeline

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

No annotations are present, so the description must carry the behavioral weight. The phrase 'same rows an anonymous visitor sees' strongly implies a public, read-only list and reveals the return composition. It does not explain caching, rate limits, or timezone handling, but the description gives an adequate transparency baseline.

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 sentence with no wasted words: it states the resource, source, public behavior, and what a returned row contains. The key discriminator ('anonymous visitor sees') 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 low-complexity, one-parameter command, the description is essentially complete. It names the response row contents, which matters because there is no output schema. It only stops short of stating a precise timezone or daily cutoff for 'today', which is a minor gap.

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 is already 100% covered for the single limit parameter, including its range and default. The description does not add any further parameter nuances, which is appropriate under the baseline-3 rule 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 identifies a specific verb-resource pair: retrieving today's top-scoring published tickers from tapeline.io. It also states the exact scope (the list an anonymous visitor sees) and the included row fields, which distinguishes it from per-ticker tools like get_ticker_record and get_ticker_score.

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 makes its use case clear: this returns the daily published top picks, not a specific ticker's record or score. It gives context about the public nature of the data, but it does not explicitly name alternatives or state when not to use this tool.

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 behavioral burden. It discloses remarkably concrete behavior: it returns every occurrence, includes both wins and losses, and anchors performance to SPY for the next session. It doesn't mention ordering or edge cases, but the key behavioral scope is easy to see.

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 dense sentence with no filler: it captures scope, measurement, and completeness. It is not perfectly structured as a formal tool definition, but it earns its length.

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 tool this is nearly sufficient. The description conveys what an agent will get back, including negative outcomes, and the input schema fully documents symbol. The absence of any output schema makes a more explicit mention of the expected return type would help, but does not prevent 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?

There is only one parameter with 100% schema description coverage via the symbol example and type string. The tool description adds no further parameter nuance, so it does not go beyond what the schema already provides.

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 says exactly what the tool does: it returns every daily top-10 publication for a specific ticker and how each pick resolved against SPY the following session. This clearly distinguishes it from siblings that deal with daily picks or ticker scores by making the single-ticker historical focus 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 use case is implied by the text — you call this when you want one ticker's pick history rather than a daily pick list or a score. However, there is no explicit when-not-to-use guidance or mention of alternatives such as get_daily_picks.

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 burden of behavioral disclosure. It conveys a read-like lookup, a 'current' snapshot, score bounds, and a single-ticker scope. It does not mention error cases or freshness limits, but for this simple operation the disclosure is reasonably adequate.

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 one dense, high-value sentence that front-loads the output and instantly explains the main use case. There is no 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?

Given a single parameter, no output schema, and no annotations, the description still explains the return fields well: score, signal label, confidence, one-line reason, and range. An agent can understand what the tool offers and call it with just the symbol.

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 covers the only parameter completely, including type, required status, and examples like NVDA or BRK.B. The description only reinforces the existing 'US ticker' constraint and adds little beyond what the schema already provides.

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 clear action (get), a specific resource (a single US ticker's Tapeline score), and exactly what is returned: six-factor score, confidence, and reason. This is distinct from sibling tools like get_ticker_record or search_tickers.

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 explicitly says to use this tool when asked what Tapeline says about a specific stock, so the primary trigger is clear. It does not name alternative tools or exclusion cases, but the guidance is sufficient for this simple lookup.

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 states that the record is public, never-edited, and includes a sample-size qualifier, which gives an agent useful context about reliability and trustworthiness. It does not dwell on side effects, but this is a read-oriented 'get' tool and the description makes that clear.

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 whole description is one dense sentence with no filler. It front-loads the core fact (public, never-edited record), enumerates all included metrics, and ends with a usage directive, earning every word.

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 tool with no parameters and no output schema, the description is complete. It names the data source, the metrics returned, the caveat, and when to call it. Nothing else an agent needs to invoke or interpret the result is 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?

The input schema has no parameters, so there is nothing to explain parameter-by-parameter. The described content and qualifier of the record still adds useful semantic context beyond the empty 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?

The description clearly identifies the tool as returning Tapeline's public, never-edited performance record, listing the specific metrics it contains (number of picks, sessions, SPY beat rate, median alpha). It distinguishes itself from the sibling tools by focusing on the overall published track record rather than daily picks, individual tickers, or scores.

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 gives an explicit usage rule: call this before stating any Tapeline performance figure. It does not explicitly describe alternatives or when not to call it, but for a zero-parameter overview tool, the stated trigger condition is clear enough to guide selection.

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 present, so the description must carry behavioral disclosure. It does reveal an important scope constraint ('covered tickers') and the accepted input forms. However, it does not disclose what happens when the query returns multiple matches or zero matches, nor whether the result is a single symbol or a list, which is meaningful for a search tool with no output schema.

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 just two sentences. The first sentence states what the tool does, and the second explains where it fits in the workflow. There is no filler or redundant detail.

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 single-parameter tool with low complexity, the description covers the essential context: what the tool looks up, what input it accepts, and when to use it relative to the other tools. The main gap is not explaining the response form when multiple or zero matches exist, but the description is still adequate for an agent to invoke the tool 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?

Schema description coverage is 100%; the schema already describes query as 'Symbol or company name.' The description only repeats that information and adds no additional semantics, so the baseline score 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 uses a specific verb and resource ('Look up covered tickers by symbol or company name') and clearly frames the tool as a resolver that converts company names to symbols. This distinguishes it from the get_* sibling tools, which presumably operate on an already-identified ticker.

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 second sentence gives explicit workflow context: use it to resolve a company name into a symbol 'before calling the other tools.' This tells the agent when the tool is useful. However, it does not state when NOT to use it, such as when the agent already has a symbol and should call a get_* tool directly.

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