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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds that it returns one row per angle with specific metrics, which is helpful context. However, it doesn't mention any performance implications, aggregation details, or limitations beyond the output structure. For a simple read-only stats tool this is adequate but not rich; a 3 reflects that the description adds some value but doesn't go beyond what annotations imply.

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 earning its place: the first states the core function, the second gives concrete usage triggers, the third details the output rows. It is front-loaded with the purpose and avoids any filler, making it efficient for an agent to parse.

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, read-only statistics tool with an output schema present, the description is complete. It explains what the tool does, when to use it, and what the output contains, without needing to cover params or return format (since output schema handles that). No gaps exist for an agent to call it 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 tool has zero parameters, so the schema trivially covers 100% and there is nothing for the description to explain. The baseline for 0 parameters is 4, and the description appropriately focuses on output semantics rather than params. No additional parameter documentation is needed.

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 per-wall-angle statistics for comparison, with a specific verb ('Return') and resource ('per-wall-angle statistics'). It also lists concrete example queries (comparing angles, hardest/most climbed, flash rate by angle) that distinguish it from sibling stats tools, so an agent can select it unambiguously.

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 explicitly specifies when to use this tool: 'Use when the user asks to compare angles, which angle they climb hardest or most at, or flash rate by angle.' This gives strong contextual triggers, though it doesn't name specific alternative tools or state exclusions. That would push it to 5, but the guidance is clear enough for typical 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 cover read-only and non-destructive behavior. The description adds useful behavioral details: the pyramid is ordered hardest first and includes flash rates, and the angle parameter filters by wall angle. It does not contradict annotations and provides context beyond them.

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, no waste. The first sentence states the core function; the second gives usage guidance and the filter. The primary purpose is front-loaded and 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?

The tool has an output schema, so return format is covered elsewhere. With one optional parameter explained, clear usage guidance, and annotations for safety, nothing an agent needs to call it correctly is missing. Complexity is low, and the description is fully sufficient.

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 has 0% description coverage for the 'angle' parameter, so the description must explain it. It does: 'Optional wall-angle filter.' This gives the parameter meaning (a filter on wall angle) and clarifies it is optional. Though it lacks units or range, it sufficiently compensates for the schema gap.

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 a send pyramid with sends per grade, hardest first, and flash rates. It uses a specific verb and resource, and the usage triggers ('grade pyramid', 'distribution of grades', 'flash rate per grade') distinguish it from siblings like kilter_get_hardest_sends and kilter_get_progression.

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 lists when to use the tool ('when the user asks about their grade pyramid, distribution of grades, flash rate per grade, or how solid they are at a level') and mentions the optional angle filter. However, it does not explicitly name alternatives or state when not to use it, so it lacks 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?

Annotations already declare the tool read-only, open-world, and non-destructive, so the description's added details are valuable: the uniqueness constraint ('unique per climb and angle'), the sort order ('hardest first'), and the default limit. These behavioral traits go beyond what annotations or the schema alone provide.

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 with no filler. The primary action and result semantics are front-loaded, followed by usage guidance and key parameter details. Every sentence 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?

Given the tool's simplicity, two optional parameters, existing annotations, and output schema, the description is complete enough for an agent to select and call it correctly. It covers scope, ordering, uniqueness, filtering, and limit behavior without needing to re-describe return values.

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 0%, so the description carries the burden for explaining parameters. It adds some meaning for both parameters: 'angle' is described as an optional wall-angle filter, and 'limit' is given a default of 10. However, it leaves ambiguity about the expected angle format and what exactly 'limit' limits (though 'hardest first' implies number of climbs returned).

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 ('Return') with a specific resource ('the user's hardest sent climbs') and defines the result set precisely ('unique per climb and angle, hardest first'). It clearly distinguishes this tool from siblings like kilter_get_sends by focusing on 'hardest' and personal bests.

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 explicitly states when to use the tool: 'Use when the user asks about their hardest sends, best climbs, max grade, or personal bests.' It provides clear usage context, though it does not explicitly name alternatives or state when not to use this tool. This is one notch below fully explicit 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 establish that this is a safe read-only operation, and the description adds useful behavioral context beyond that: entries are returned newest first, each entry represents a climb/angle/date/tries combination, and filter semantics are explicitly defined. It does not cover every possible edge case, but it meaningfully supplements the annotation 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?

The description is compact and front-loaded, with the core purpose in the first sentence and use cases immediately after. The filter list is dense but scannable, with defaults, units, and format specified in every relevant case. No sentence is redundant.

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?

All five optional parameters are semantically covered, the return ordering is specified, and the output schema exists, so return-value details do not need to be in the description. The description gives an agent everything needed to invoke the tool correctly and interpret its basic behavior.

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 0%, so the description carries full responsibility for explaining parameters. It clearly documents all five filters: limit with default and max, angle in degrees, topped as sends vs unsuccessful attempts, and start/end date format with inclusivity. This fully compensates for the schema's lack of 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 opens with a specific verb and resource: 'Return the user's Kilter logbook entries, newest first.' It further clarifies the unit of data ('one climb at one wall angle on one date'), which distinguishes it from sibling tools like kilter_get_sends or kilter_get_sessions. This makes the tool's scope immediately identifiable.

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 use cases: 'when the user asks about recent Kilter climbs, attempts, what they climbed on a date, or wants raw history.' It does not explicitly name sibling tools or state when not to use this tool, but the when-to-use guidance is clear and actionable enough for an agent to route to it correctly.

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 destructiveHint=false, so the description doesn't need to restate safety. It adds valuable behavioral context beyond annotations: ordering of results, the list of per-period metrics (sessions, sends, unique climbs, flashes, attempts, hardest send/flash), and the optional wall-angle filter. This enriches the agent's expectation of output without contradicting annotations.

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 compact and front-loaded with the core purpose. The 'Use when' clause provides immediate usage context, followed by parameter details. Every sentence adds value; 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 read-only tool with only two optional parameters and an existing output schema, the description covers purpose, usage triggers, parameter semantics, and expected output structure. The output schema presumably details the return shape, so the description need not repeat that. Nothing essential 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?

Schema description coverage is 0%, so the description must compensate. It does: it defines period as 'month' (default) or 'week' and calls angle an 'optional wall-angle filter'. This adds meaning beyond the bare schema. It could be more precise about angle's allowed range or units, but it's sufficient for an agent to understand both 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 opens with a specific verb-resource pair: 'Return climbing progression over time' plus an ordering constraint ('oldest period first'). It clearly distinguishes this tool from siblings like kilter_get_grade_pyramid or kilter_get_hardest_sends by focusing on time-based progression.

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?

Explicitly states when to use: 'Use when the user asks how they have progressed, trends, whether they are improving, or for a month-by-month/week-by-week view.' This gives the agent clear trigger conditions and even mentions the period parameter values, leaving no ambiguity about 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?

Annotations already mark the tool read-only and non-destructive, and the description adds meaningful behavioral detail: a project is tracked per (climb, angle), sending it at another angle does not remove it, and results are sorted by most recently tried then most attempts. No contradiction with annotations.

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?

Every sentence earns its place: core definition, when to use, projection identity, sort order, and optional filter. The description is front-loaded and contains 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?

The description covers the result definition, sort order, and optional angle filtering, with an output schema present to document return values. The only notable gap is the undocumented limit parameter, which is minor given its simple role and default.

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 0%, so the description must compensate. It explains that angle is an optional filter and clarifies per-angle semantics, but it never describes what the limit parameter controls beyond the schema default of 50.

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?

Opens with a precise definition: 'Return the user's projects: climbs attempted but never topped at that wall angle.' This clearly identifies the verb, resource, and the distinguishing project concept, allowing an agent to separate it from sibling tools like get_sends or get_hardest_sends.

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?

Provides an explicit trigger: 'Use when the user asks what they are working on, unfinished climbs, or what to try next.' It does not name sibling alternatives or state when not to use the tool, but the given context is clear enough to prevent common misuse.

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 destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it explains the meaning of the 'flash' status, the default limit (50) and maximum (500), and the date format (YYYY-MM-DD). It does not disclose pagination behavior or whether filters are inclusive, but for a read-only query tool this is sufficient given the annotations.

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 with zero filler. The first sentence front-loads the core purpose and ordering, and the second sentence packs in usage context, the flash clarification, and all filter details. Every word earns its place, and it is structured to give the most important information first.

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 moderate complexity (4 optional parameters), the presence of an output schema, and the annotations covering safety, the description is complete. It explains the filters, the default behavior, and the meaning of a key status. It doesn't cover edge cases like inclusive date ranges or the exact output shape, but the output schema presumably handles that. The usage guidance is also present, so an agent has what it needs to call 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?

The schema has 0% description coverage, so the description carries the entire burden of explaining parameters. It clearly defines each filter: limit with default and max, angle in degrees, and start_date/end_date in YYYY-MM-DD format. This fully compensates for the missing schema descriptions and leaves no ambiguity about parameter meaning or constraints.

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 verb ('Return') and resource ('climbs the user has topped (sent)'), and adds the ordering ('newest first'). This is specific and distinguishes it from sibling tools like kilter_get_hardest_sends or kilter_get_grade_pyramid, which focus on different aspects. The clarification that 'flash' means topped on the first try further sharpens the purpose.

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 explicitly says 'Use when the user asks about their sends, ticks, completed climbs or flashes,' which gives clear context for when to invoke this tool. It does not mention alternative tools or when not to use it, but the use cases are specific enough that an agent can route appropriately. The filter details (limit, angle, date range) also imply the tool is for querying sends with optional parameters.

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 destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: sessions are grouped by calendar day, ordered newest first, and the limit defaults to 5. It also discloses that each session includes every climb logged that day, which is a meaningful behavioral trait beyond the 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 compact and front-loaded: the first sentence states the core function, the second gives usage context, and the third lists return contents and the default. Every sentence earns its place with no 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 tool's simplicity (1 optional parameter, no nested objects, output schema present), the description is nearly complete. It covers what the tool returns, when to use it, and the default limit. It doesn't describe pagination or the exact output schema structure, but the output schema exists and the tool is simple enough that this 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?

Schema description coverage is 0%, so the description must compensate. It does mention 'limit defaults to 5' and implies the limit controls how many sessions are returned. However, it doesn't explicitly state that limit is the only parameter or describe edge cases (e.g., null limit behavior), but for a single optional parameter with a default, the description provides enough meaning.

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 ('Return'), a clear resource ('recent climbing sessions'), and a defining characteristic ('entries grouped by calendar day, newest first'). It also lists the content of each session (angles, sends, flashes, attempts, hardest send, every climb logged that day), which distinguishes it from sibling tools like kilter_get_logs or kilter_get_sends.

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 explicitly says when to use this tool: 'when the user asks how their last session went, what they climbed yesterday, or wants to compare sessions.' This provides clear context and implicitly distinguishes it from alternatives like kilter_get_hardest_sends or kilter_get_progression, which would be used for different questions.

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, openWorldHint=true, and destructiveHint=false. The description adds useful behavioral context beyond that by defining the result as a compact aggregate of the whole Kilter history and enumerating the totals included, such as sends, flashes, attempts, and hardest send/flash.

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 with the core action and resource front-loaded. The second sentence efficiently adds when to use it and what totals it covers, with relevant example queries that earn their 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?

Given zero parameters, annotations confirming a safe read operation, and the presence of an output schema, the description is complete. It tells an agent when to invoke the tool and what kind of information it will receive.

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 accepts zero parameters and schema description coverage is 100%, so parameter semantics require no additional explanation. Baseline for 0 parameters is 4; the description does not need to compensate for missing parameter docs.

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?

Description names the action ('Return'), the resource ('compact overview of the user's whole Kilter history'), and the scope ('whole Kilter history'). It is clearly distinct from sibling tools that return granular lists or specific statistics.

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 explicitly says 'Use first' and gives concrete triggers: broad questions like 'how is my climbing going?' and needs for totals. It does not explicitly name sibling alternatives or state when not to use it, so it misses the top tier but provides clear context.

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