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

With no annotations, the description discloses key behavioral traits: 'It shows evidence only and lets you judge what counts as done' — indicating a read-only, non-judgmental analysis. It also clarifies that the tool attaches data, implying no mutation or destructive actions, which is useful transparency.

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 four sentences, reasonably concise. The first sentence is slightly jargony, but the second directly explains the mechanism. The third sentence ('single proven lever') is somewhat promotional yet not excessive. Front-loading is adequate.

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 3 params, no required fields, no output schema. The description explains the core workflow (attach current sprint data to previous actions) and the output's nature ('shows evidence only'). It lacks specifics on what 'relevant data' includes, but the overall context is sufficiently conveyed for a simple 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?

Schema coverage is 100%, so parameters are already documented. The description adds context by tying 'previous retro's action items' to the previousActions param and 'THIS sprint' to sprintId, but does not provide additional syntactic or semantic detail beyond the 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 states the tool's function: 'Give the previous retro's action items and it attaches THIS sprint's relevant data to each' — a specific verb-resource pair. It also distinguishes itself from siblings like retro_metrics or retro_brief by focusing on action-item evidence and follow-through.

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 context ('Reviewing prior actions is the single proven lever on retro follow-through') but does not explicitly compare with sibling tools or state when not to use it. It offers a strong rationale but lacks exclusionary 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?

With no annotations, the description carries the full burden of disclosing behavior. It adds useful context by stating the prompts are grounded in real anomalies and framed as questions, not verdicts. However, it does not disclose side effects, permissions, or output structure, which prevents a higher score.

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 short, front-loaded sentences that deliver the core purpose immediately and include only valuable details. Every phrase earns its place without unnecessary 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 tool has only two optional parameters and no output schema, and the description adequately conveys that the output is a set of open questions for discussion. It could specify quantity or format more precisely, but for this simple tool the description is largely 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?

The schema already describes both parameters with 100% coverage, so the baseline of 3 applies. The description does not add any additional meaning or guidance for boardId or sprintId beyond what the schema 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 clearly identifies the tool as providing open discussion questions for a retro board, grounded in real anomalies from the closed sprint. It distinguishes itself from sibling tools by emphasizing open-ended questions rather than metrics, summaries, or action items, though it lacks an explicit verb such as 'generates' or 'lists.'

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 clear context for use: it is for the retro board and intended to start conversation, not to pass verdicts. It implies when this tool is appropriate and differentiates from siblings, but does not explicitly name alternatives or state when not to use it.

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 and excels by disclosing the non-network read-only nature, the possibility of a synthetic demo sprint, and the alternative --check flag. This goes beyond basic purpose and sets accurate expectations.

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 succinct sentences, front-loaded with the core purpose, followed by relevant scope details and a caveat. No unnecessary 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?

For a zero-parameter tool with no output schema, the description fully covers what it does, what it does not do, and how to verify live connections. It is complete within its simple context.

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 zero parameters, so schema coverage is effectively complete. The description does not need to explain parameter details, and the baseline for zero parameters 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 'Show which data sources are configured' and enumerates the specific sources (Jira, optional GitHub/Slack enrichment, synthetic demo sprint). It distinguishes itself from sibling tools that focus on retrospective content rather than configuration listing.

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 notes that the tool 'Does not hit the network' and directs users to 'run the server with --check to verify live connections', providing a clear when-not-to-use and an alternative approach for live verification.

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?

The description discloses that every line is backed by specific data sources (metric, ticket, PR, Slack thread), frames the output around process not individuals, and flags recurring themes. These are meaningful behavioral traits beyond the basic generation, especially given no annotations are provided.

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 tool's purpose and key behavioral characteristics. Every sentence provides substantive information with no 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 description outlines the four sections of the retrospective and notes data grounding and thematic flagging, effectively explaining the expected output despite the absence of an output schema. Minor details like output format are not specified, but overall it is suitably complete for a tool with only two optional parameters.

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 already documents both optional parameters with clear descriptions, achieving 100% coverage. The tool description adds no additional parameter-specific information beyond what the schema 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 clearly states the tool generates a data-grounded sprint retrospective with four named sections (What went well, What did not, Action items, Discussion prompts). It distinguishes from sibling tools by combining metrics, prompts, and action items into a single comprehensive brief.

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 the tool's default behavior (most recently closed sprint) and output scope, but does not explicitly name alternatives or when-not-to-use scenarios. The sibling tool list suggests narrower tools exist, but the description doesn't reference them.

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. It discloses the scope (closed sprint, comparison with prior sprint) and the output content (detailed metrics list). It does not explicitly state it is read-only, but that is strongly implied by the nature of metrics retrieval.

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, consisting of two sentences. The first sentence front-loads the core purpose with a dense but relevant list of metrics; the second adds context. Every phrase contributes, though the list could be seen as slightly exhaustive.

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?

Since there is no output schema, the description does well to enumerate the returned metrics and establish the comparison baseline. It does not explain parameter defaults or prerequisites, but the schema fills that gap. Overall, it gives a clear picture of what the tool offers.

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 clearly described. The tool description adds no parameter-specific meaning beyond the schema, so the 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 specifies the tool's function as retrieving quantitative metrics for a retro on the closed sprint, enumerating specific measurements. It distinguishes itself from siblings by calling itself 'the evidence base the brief draws from', implying a distinct data-provision role.

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 phrase 'evidence base the brief draws from' provides clear context for when to use this tool—when raw numbers are needed for a retro. However, it does not explicitly name alternatives or state when not to use it, so it stops short of full exclusion 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?

With no annotations, the description carries the burden of behavioral disclosure. It explains what the tool compares and that it lists problem themes, implying a read-only analysis. However, it does not explicitly state whether it modifies any data, require permissions, or describe the output format, leaving some behavioral aspects undisclosed.

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 extremely concise, using two sentences to cover core functionality and usage guidance. It is front-loaded with the main comparison action and metrics, with no 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 description provides a solid overview of the tool's function and output (comparison metrics and problem themes). While it lacks an output schema or explicit return-value details, the description sufficiently covers what the tool delivers. The absence of annotations and the tool's analytical nature make this reasonably complete, though a note on read-only behavior would improve it.

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 provides 100% coverage with clear descriptions for both parameters (boardId and sprintId), including defaults. The tool description adds no additional parameter semantics, so the 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 compares the closed sprint to the previous one, enumerating specific metrics (completion, scope, carryover, reopens, cycle time, velocity) and lists recurring problem themes. This specific verb+resource combination distinguishes it from sibling tools like retro_metrics, which likely focus on single-sprint analysis.

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 final sentence 'Use it to tell a one-off from a pattern' provides explicit usage context, indicating when this tool is appropriate. However, it does not explicitly mention alternatives or exclusions relative to sibling tools like retro_metrics or retro_brief, so it falls short of a 5.

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