flotilla-mcp

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

With no annotations, the description carries the behavioral burden. It discloses exact return values (pending/success/failure), the error signal ('ERROR:'), and the guarantee that it never raises. This is substantial transparency, though it omits details like authentication or rate-limit behavior.

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 front-loaded with the core action and immediately gives precise outcome semantics. Every clause contributes useful information; there is no repetition 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?

This is a simple one-parameter read-only tool with thorough return-value documentation and explicit failure behavior. Even without an output schema or annotations, an agent has everything needed to call it correctly and interpret the result.

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% and the single parameter pr_number is already described as 'The pull request number to check.' The description adds context about the head commit but no additional parameter-level meaning, so the baseline 3 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?

States a specific verb ('Get'), a precise resource ('combined CI status for a pull request's head commit'), and the data source ('GitHub's Checks API'). This clearly distinguishes it from sibling tools like run_tests or submit_pr.

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 the use case clear: check a PR's combined CI status without running tests or modifying anything. It doesn't explicitly name alternatives or exclusions, but the context is unambiguous enough for selection among the listed siblings.

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, and it does so thoroughly. It discloses that PRs are excluded, defines the exact output format for matches and empty results, specifies the 'ERROR:' prefix on failure, and guarantees the tool never raises. This is exemplary behavioral disclosure.

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 well-ordered: purpose, exclusion, usage context, then return behavior. Every sentence contributes a distinct piece of information 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?

For a one-parameter list tool with no output schema and no annotations, the description covers everything an agent needs: what it lists, what it excludes, when to use it, what it returns, and how failures present. Nothing critical 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 100%, so the baseline is 3. The schema already documents 'label' as 'Issue label to filter by', and the description adds only the context that the label applies to open issues and is used in the empty-result message. This is adequate but not additive 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 states a specific verb ('List'), a specific resource ('open GitHub issues carrying the given label'), and an important exclusion ('pull requests are excluded'). This clearly distinguishes it from sibling tools like start_issue or submit_pr without needing to inspect their schemas.

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 'Use this to discover work before calling start_issue', giving a clear workflow context. It does not enumerate when-not-to-use cases for every sibling, but the sequential relationship to start_issue is sufficient guidance for the primary use case.

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, and it does so thoroughly. It explains path refusal rules, return value formats ('REFUSED: ...', 'ERROR: ...'), and the guarantee that it never raises. This is exactly the kind of non-obvious behavior an agent needs to know.

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, followed by path constraints and return contracts. Every sentence earns its place; there is no fluff or repetition of unrelated details.

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 two required parameters, no output schema, and no annotations, the description is complete: it covers the prerequisite, path resolution rules, refusal/error behavior, and success return format. An agent has everything needed to call the tool correctly and anticipate its outcomes.

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%, which sets a baseline of 3, but the description adds meaningful value beyond the schema by specifying that relative_path is resolved against the issue workspace, explaining the refusal categories, and clarifying the error/refusal return strings. This helps the agent understand the actual runtime behavior for each parameter.

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: 'Read a file's contents from the workspace start_issue created for this issue.' It clearly identifies the operation, the scope, and the relationship to sibling tools like write_file and start_issue, so an agent can distinguish it without ambiguity.

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 when to use the tool: to read a file within an issue-specific workspace, and it states the prerequisite that start_issue must have been run first for the issue_number. It does not explicitly name alternatives or state when not to use it, but the context is strong enough for correct 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?

With no annotations, the description carries the full behavioral burden, and it does so thoroughly. It discloses that the tool never mutates, specifies the exact response prefixes including REFUSED and ERROR cases, and states that it never raises.

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 uses three focused sentences and front-loads the action. Every sentence earns its place: what it does, that it is non-mutating, and the exact result contract.

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?

Even without an output schema, the description documents return value behavior, error handling, refusal conditions, and timeout semantics. Combined with fully described parameters, the definition provides everything an agent needs 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?

Schema description coverage is 100%, so the schema already documents both parameters, including the pytest path usage and refusal conditions for service_relative_path. The description adds only marginal parameter-related context, 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 states a specific verb and resource: run the repository's own pytest suite for one service inside the issue workspace. It also distinguishes itself from mutating siblings by explicitly saying it never commits or modifies anything.

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 conveys when to use the tool: after the issue workspace exists, to execute that service's tests with a timeout. It does not name alternative tools or explicit when-not conditions, but the context is clear enough that an agent can select it safely.

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 disclosure burden and meets it thoroughly. It describes workspace isolation, branch creation/resume behavior, the single-active-workspace constraint, the success/error return contract, and the fact that it never raises an exception.

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 purposeful sentences with no filler. It front-loads the core action, then provides ordering guidance, idempotency/error behavior, and the return contract. Every sentence contributes operational 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 single-parameter tool with no output schema and no annotations, it is nearly complete: return format, failure behavior, workspace semantics, and ordering are all specified. It does not explicitly state how 'target repository' is determined, but in an issue-scoped workflow this is largely inferable from 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?

Schema coverage is 100% and the schema already describes issue_number as 'The GitHub issue number to start work on.' The description adds extra meaning by showing exactly how issue_number is used in the branch name selfdev/issue-<issue_number>, which helps the agent understand the parameter's effect.

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 and resource: 'Begin work on a GitHub issue: clone the target repository into a fresh, isolated per-issue workspace and create... a branch.' It also distinguishes itself from siblings by explaining that read_file, write_file, run_tests, and submit_pr all operate on the workspace this tool creates.

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 call this first, before read_file, write_file, run_tests, or submit_pr, and explains why: those tools operate on the workspace this tool creates. It also warns that calling it again for an already-active issue returns an error instead of clobbering the existing workspace, giving clear when-to and when-not-to conditions.

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 behavioral burden and does so thoroughly: it declares the destructive workspace cleanup, the no-merge/no-force-push guarantees, the GitHub repository prerequisite, exact return strings, and the error path that preserves the workspace. This is well beyond a minimal 'submits a PR' statement.

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?

Four or five dense sentences each carry essential information: action sequence, safety constraints, prerequisite, return/error behavior. There is no fluff or repetition, and the most important lifecycle information appears 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?

For a complex, destructive terminal tool with no output schema, the description covers prerequisites, effects, failure semantics, and return format. An agent can call submit_pr correctly and predict consequences without needing additional 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?

Schema coverage is 100%, so the schema already documents all three parameters and their meanings. The description adds no extra parameter-level detail beyond what the input schema provides, so the baseline 3 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 names a specific workflow with a concrete verb and resource: commit the workspace, push the selfdev/issue-<issue_number> branch, and open/reuse a PR, then destroy the workspace. This clearly distinguishes it from sibling tools like start_issue or check_pr_status, which only start or inspect work.

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 opening 'Finish work on an issue' establishes the intended point in the workflow, and the issue_number parameter notes the workspace must have been started with start_issue first. It does not explicitly name alternatives or state when not to call it, but the context is 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It fully discloses write caps (default 5, configurable), that refused writes don't count against the cap, and all possible return values ('OK', 'REFUSED', 'EXHAUSTED', 'ERROR') including the guarantee that it never raises. Path restrictions are also detailed.

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, front-loaded with the core purpose, then path validation, then caps and return behavior. Every sentence adds unique value with no repetition or filler. The structure is logical and easy 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 write tool with no output schema and no annotations, the description covers all essential operational aspects: what it does, how paths are validated, attempt limits, exact return values, and the guarantee of not raising exceptions. It also ties into start_issue as a prerequisite. Nothing critical is missing 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?

Schema description coverage is 100% – all three parameters (content, issue_number, relative_path) are already described with sufficient detail in the schema. The description adds a cross-reference to read_file for relative_path validation and mentions the fleet manifest check, but these are essentially re-statements of schema content. It adds no new semantic meaning beyond the schema, so a 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 ('Create or overwrite a file') with a clear resource (file inside the issue workspace) and distinguishes itself from read_file by its write semantics. It also references the prerequisite start_issue, leaving no ambiguity about what the tool does.

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 the tool is for writing files and references read_file for path-check consistency, but it does not explicitly state 'use this for writing, read_file for reading' or mention any exclusions. The start_issue prerequisite is noted, providing clear context, but alternatives are not spelled out.

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