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 implies a mutation ('adds') and scoping to the active project, but says nothing about persistence, permissions, ordering/deduplication, or what happens on success. This is a significant gap for a write tool with zero annotation coverage.

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?

A single well-formed sentence with the action front-loaded and no waste. It is appropriately brief for a one-parameter tool.

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?

An output schema exists, so return values need not be explained. For a simple single-param tool this is close to adequate, but the lack of any behavioral or scoping detail on a mutation with no annotations leaves 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 single parameter has 0% schema description coverage, so the description must compensate. 'Actionable task' gives loose meaning to task_text but adds no format, length, or content guidance beyond the parameter name itself.

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 ('adds') and resource ('a new actionable task to the active project checklist'), which is clear. It does not, however, explicitly differentiate itself from siblings like cockpit_toggle_task or cockpit_get_ready_tasks, so an agent must infer the boundary.

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?

There is no when-to-use or when-not-to-use guidance, and no prerequisites such as what 'active project' means or how it is selected. Alternatives are not mentioned.

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 behavioral burden. It discloses the destination file ('decisions.md'), but for a write operation it says nothing about whether the file is created if absent, whether records are appended or overwritten, ordering, permissions, or whether the write is reversible.

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 that front-loads the action and resource, then the destination, then the rationale. Nothing is padded or repeated.

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?

An output schema exists, so return values need no explanation, but the definition is thin for a 5-parameter mutation tool with zero annotation coverage and 0% schema descriptions. It arguably omits only the input-field guidance, but that omission is large enough to leave the definition materially incomplete.

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% across 5 parameters, and several parameter names (context, decision, consequence) are ambiguous without domain framing. The description explains none of them, so an agent gets no help mapping intended content to the correct fields beyond general ADR familiarity.

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 and resource ('Records a new Architecture Decision Record') plus the target artifact ('decisions.md'), which clearly separates it from siblings like cockpit_add_task or cockpit_toggle_task. The stated rationale ('to prevent conflicting implementations') adds intent, though it stops short of naming an alternative tool.

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 'to prevent conflicting implementations' implies the situation that motivates recording an ADR, so usage is weakly inferable. There is no explicit when-to-use vs when-not guidance and no reference to any sibling tool, leaving the agent to infer the trigger.

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 discloses the returned content well, which implies a read-only, aggregate query, but it never explicitly states the operation is non-mutating, nor does it mention side effects, caching, or permission requirements.

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?

A single tight sentence that front-loads the resource and then lists the contents. No filler, though a short 'use this first for project state' clause would have earned more.

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?

With an output schema present, return values need no further explanation, and with zero parameters the call surface is trivial. The description is sufficient for correct invocation, only lacking explicit read-only/usage framing.

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 takes zero parameters, so there is nothing to document and the schema is trivially complete. Baseline 4 applies; the description correctly describes a no-argument getter.

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 verb ('Returns') and resource ('project overview'), and enumerates the payload contents (active milestone, git status, recent ADRs). It is clear what the tool fetches, though it does not explicitly distinguish itself from siblings like cockpit_get_ready_tasks.

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?

There is no statement of when to use this tool, when not to, or which sibling it replaces. An agent must infer from the name that this is the entry-point summary call.

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. It usefully discloses the exclusion semantics (completed and blocked tasks are omitted) and the read-only nature implied by 'Returns', but says nothing about ordering, result limits, or whether readiness is computed at call time.

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?

A single front-loaded sentence with no filler, and the two exclusion conditions are stated before the payoff phrase 'ready to work on'. Every clause 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?

An output schema exists, so return values need not be described, and with zero parameters there is little else to cover. The description is close to complete for a simple no-arg read tool, though ordering and limit behavior remain unaddressed.

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 takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. No parameter semantics are missing.

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 ('Returns ... tasks') and narrows the scope with two filter conditions ('uncompleted', 'unblocked and ready'). It is clear what subset of tasks is returned, though it never names the sibling (cockpit_get_overview) that returns the broader picture, so differentiation is implied rather than 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?

Usage is only implied: an agent can infer you call this when you want actionable work, but the description gives no when-to-use framing, no prerequisites, and no comparison against cockpit_get_overview or cockpit_toggle_task. Adequate but leaves routing to inference.

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 and falls short. It does not say whether the note is appended or overwrites a prior handover, whether it requires prior session state or auth, whether the call is idempotent, or whether it actually ends the session. For a state-persisting session-boundary operation, those are material omissions.

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?

A single front-loaded sentence, with the protocol label first and the operational gloss second. No filler, though the parenthetical nickname consumes space without adding invocation 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?

An output schema exists, so return values need no explanation, and the one-line purpose is coherent with the sibling set. However, with zero annotation coverage and undocumented required parameters, the description leaves the agent guessing about persistence semantics and field content, which is thin for a session-closing write.

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% for two required parameters, and the description adds no meaning beyond the generic term 'handover note'. Nothing explains expected format, length, or what 'author' should contain (user id, agent name, free text).

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 (saves) and resource (handover note) and frames it as a session-ending handover step, which clearly separates it from sibling tools like cockpit_add_task or cockpit_create_adr. The metaphor-heavy name is redeemed by the plain-language gloss, though the description never says whether saving also terminates the session.

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?

Gives an explicit trigger: call it before concluding an agent session. That is clear usage context. It does not name alternatives or state when not to use it, so it stops 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.

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

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing beyond the one-line purpose: no indication of whether it reads cockpit state, whether the result is deterministic, whether it depends on existing context/tasks, or what the caller should supply prior to invoking it.

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?

A single front-loaded sentence with the key noun phrase early and the agent examples in a low-cost parenthetical. Little waste, though 'optimal' adds no verifiable meaning.

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?

An output schema exists, so return value documentation is legitimately omitted. However, for a tool whose sole purpose is producing a handover prompt, the description never explains what input context is required or how 'instruction' shapes the output, leaving a meaningful 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 for two undocumented parameters. It partially clarifies 'target_agent' through the example agent names, but says nothing at all about 'instruction'—the most ambiguous parameter, which has only a default of empty string in 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 names a specific verb ('synthesizes') and a concrete resource ('handover prompt for another agent'), with examples that disambiguate it from the cockpit management siblings. It is clear what the tool produces, though 'optimal' is unquantified filler rather than substantive detail.

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 when-to-use guidance, no prerequisites, and no mention of alternatives among the sibling cockpit_* tools. The examples of target agents hint at applicable contexts but the agent is left to infer when this tool should be chosen at all.

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 behavioral burden. It only states that a task is marked completed or pending; it omits whether the operation is idempotent, what permissions are needed, what happens when 'completed' is omitted, and whether the change is reversible.

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?

A single, well-formed sentence with zero wasted words. The purpose is front-loaded and the sentence earns its place without 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?

An output schema exists, so return values need not be described, but the input schema has 0% description coverage and no annotations. The description leaves key details unstated, including the required task_id, the default behavior of completed, and any prerequisite or side-effect 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 description coverage is 0%, so the description must compensate for both parameters. It gives only an indirect hint that a completed/pending state exists, but it never mentions 'task_id', never explains its role, and never clarifies that the 'completed' boolean defaults to true or what omitting it does.

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 ('Marks') and resource ('a task as completed or pending in the project checklist'), which is clearly distinct from siblings like cockpit_add_task and cockpit_get_ready_tasks. However, it does not explicitly differentiate itself from all sibling tools or clarify the 'toggle' naming versus the explicit completed/pending states.

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 by saying it marks tasks in the project checklist, but it provides no explicit when-to-use guidance, no prerequisites, and no alternatives. It does not tell an agent when to choose this tool over cockpit_add_task or other status-related siblings.

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