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

With no annotations, the description carries the full behavioral burden. It does disclose one valuable trait — that cancellation kills the process tree, implying a destructive, non-graceful termination — but says nothing about permissions, idempotency, or behavior when the job is already finished.

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 short clause with the destructive effect front-loaded in parentheses; nothing is wasted. It is arguably too terse for the gaps it leaves, but as structure it is tight and readable.

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?

No annotations and no output schema, and the lone parameter is undocumented in both schema and prose. For a simple cancel operation the description covers the essentials (what it does, destructiveness) but omits return behavior and failure conditions.

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 the single required parameter, so the burden falls on the description, which never mentions job_id or its expected format. The description adds no parameter meaning at all.

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 (cancel) and resource (a job), and the parenthetical 'mata el árbol de procesos' clarifies the actual effect. It does not differentiate itself from potential siblings like 'cleanup' or 'wait', but the core action is unambiguous.

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 guidance on when to use this versus alternatives such as 'cleanup' or 'wait', nor any stated preconditions (e.g. the job must be running). The reader is left to infer all usage context.

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 that worktrees and branches are deleted, but says nothing about irreversibility, what happens to unmerged work, or that the operation is scoped only to artifacts this server created — the destructive consequence detail lives only in the schema's force field.

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 action verb first and no filler. The packed parenthetical carries two modes but stays readable; nothing is wasted.

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 destructive, zero-annotation tool with no output schema and only 33% parameter coverage, the description omits critical context: reversibility, safety prerequisites, and whether both selectors can be combined. It is insufficient for an agent to invoke this safely.

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 33%: force is documented, while job_id and older_than_days are bare. The description partially compensates by mapping the two selection modes ('de un job, o más viejos que N días') to those undocumented params, but adds no detail on mutual exclusivity or precedence between them.

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 (Elimina) and resource (worktrees y ramas colmena/*), plus a scope qualifier (creados por este servidor). It clearly distinguishes what gets cleaned from general-purpose siblings like cancel or merge, though it never names an alternative tool explicitly.

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: the parenthetical reveals two selection modes (by job_id, or by older_than_days), which tells the agent how to target cleanup. It never says when cleanup should be run instead of cancel or merge, nor any preconditions (e.g., branch must be merged first).

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 reveals that a summary.md artifact is created, but says nothing about where it is written, whether it overwrites an existing file, idempotency, or permission requirements for a mutation-style operation.

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; the core action and artifact appear first. It is efficiently sized for a one-parameter tool, though the parenthetical is slightly awkward.

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-param tool this is thin: no output schema means the description should explain the produced summary.md and its lifecycle, and it leaves the overlap with the summarize/handoff siblings unresolved.

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 one required parameter with 0% schema description coverage, so the description must compensate. 'La sesión de un job' loosely ties job_id to a job, but gives no format, source, or valid-value guidance for the 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?

States a specific verb (comprime) and resource (la sesión de un job) and names the concrete artifact produced (summary.md). However, it does not distinguish itself from close siblings such as summarize or handoff, and the trailing 'con handoff' is ambiguous since handoff is itself a sibling 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?

Implies usage by describing the output as 'reutilizable con handoff', which hints at a downstream workflow, but never states when to choose compact over the sibling summarize tool or any precondition for running 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?

No annotations are provided, so the description carries the full burden, yet it discloses almost nothing beyond the action itself. It does not state auth requirements, whether the session must be in a specific state to continue, what happens on failure, or how the response is delivered. Two words of scope ('mismo workdir') are the only behavioral hint.

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 short sentence with no wasted words, but it is under-specified rather than concise – there is essentially no front-loaded structure because there is so little content. Size is appropriate; information density is poor.

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 mutation-style tool with two required parameters, no annotations, no output schema, and 0% schema coverage, the description is far too thin. An agent cannot determine prerequisites, failure modes, or what a successful continuation returns.

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% and the description mentions neither parameter by name or meaning. 'message' is loosely implied by 'mensaje de seguimiento', but 'job_id' is completely undocumented and the description does not compensate for the total coverage 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?

States a specific verb (reanuda/resume) and resource (sesión de un agente), and adds the 'mismo workdir' scope. However, it does not distinguish this tool from siblings like 'run', 'handoff', or 'status', which an agent could plausibly confuse with resuming work. Purpose is clear but not differentiated.

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 no explicit when-to-use or when-not-to-use guidance, and names no alternative. It only implies usage via the 'follow-up message' phrasing. With 17 siblings, an agent receives no routing help.

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 it does disclose one real behavior: output is truncated and the full diff is written to disk. That is valuable and non-obvious. It still omits whether the job must be finished, what happens if it is still running, and whether large diffs have other limits.

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 short sentence with the core purpose front-loaded and the truncation caveat in a parenthetical, so every clause earns its place. It is terse to the point of under-specification, but not padded.

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 no annotations, no output schema, and zero parameter documentation, the description should compensate and does not. The truncation/disk note is the only substantive addition; an agent still lacks the job lifecycle context and parameter semantics needed to invoke this reliably.

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 0% and neither of the two parameters (job_id, max_chars) is mentioned in the description. The truncation note loosely gestures at max_chars, but it never explains that max_chars controls the truncation or gives a default/format for either 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?

It identifies a verb (diff) and a resource (the job's work) plus an output caveat, so the agent knows it returns a diff. However it never names what a 'job' is or which sibling produces one, so differentiation from tools like result, report, or review is left to inference.

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 guidance on when to call this versus alternatives such as result, report, or status, and no mention of prerequisites (e.g., a completed job). Usage is only implied by the tool name.

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, yet it says nothing about whether the launched agent runs asynchronously, what identifier or handle comes back, concurrency/budget limits, or how the injected summaries are merged. The schema mentions router/worker selection and isolation modes, but the description supplies none of that context.

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 compact, front-loaded sentence with zero filler. It is efficient, though for an 8-parameter orchestration tool the brevity crosses into under-specification rather than pure conciseness.

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 8-parameter, 2-required orchestration tool with no annotations and no output schema needs more than a single sentence. Missing is any explanation of the handoff lifecycle, return value, or how from/handoff_from interact.

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 high (88%), so the baseline is 3. The phrase 'resumen de otros agentes' loosely maps to handoff_from, but the description does not disambiguate the required 'from' array from the optional 'handoff_from' array, which are the two parameters most likely to confuse a caller.

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 ('lanza un agente nuevo') plus the distinguishing mechanism ('con el resumen de otros agentes como contexto'). However, it never differentiates itself from close siblings like run, run_many or continue, so an agent must infer which launch tool to pick.

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 explicit when-to-use, when-not-to-use, or named alternative. The only hint is the purpose statement itself, which is too thin to guide selection against run or continue.

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 implies a read-only listing but says nothing about pagination, ordering, default limits, or what 'recent' actually means, all of which matter for a list operation.

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?

It is only one short sentence, so it is concise and front-loaded, but brevity here reflects under-specification rather than economy of information.

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 two undocumented parameters, no annotations, and no output schema, the description is far too thin. An agent lacks the basics needed to invoke it correctly, though the general intent of listing jobs is at least conveyed.

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 parameters (limit, state), and the description never mentions them. 'Recientes' hints at a recency scope but does not explain how limit or state modify the query, so the parameters remain entirely opaque.

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 gives a verb (listar) and a resource (jobs) with a scope hint (recientes), but the tool name is a bare 'list' and nothing distinguishes it from siblings like status, result, or run. An agent cannot tell from this text alone what makes this listing different from the other job-related tools.

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 guidance, no mention of alternatives such as status or result, and no prerequisite or context. The agent must guess whether this is the right entry point for inspecting jobs.

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 one refusal condition (uncommitted changes in the destination), but says nothing about the destructive/history-rewriting nature of the merge, what the strategy field changes, permission requirements, or the return value. Partial disclosure for a mutating operation.

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 tight sentences, front-loaded with the action and followed by the workflow hint and precondition. No filler, though the positioning of the precondition last slightly buries the most important behavioral constraint.

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 mutating, annotation-less tool with no output schema and 0% schema coverage, the description covers the operation and one precondition but omits the strategy parameter's semantics and the safety profile of a branch merge. Adequate minimum but with clear 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?

Schema coverage is 0% for two parameters. The description implies what job_id means (it identifies the colmena/<id> branch) but never explains the 'strategy' enum, whose merge vs squash values produce materially different history outcomes. The most consequential parameter is left undocumented.

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 (fusiona/merges), the exact resource (la rama colmena/<id> del job) and the destination (la rama actual de su cwd). An agent can tell this is a git-merge style operation, though the sibling differentiation comes mostly from the naming of diff/review rather than from an explicit scope statement.

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 routes the agent to review first ('Manual: revisa antes con diff/review') and gives a precondition ('Se niega si el destino tiene cambios sin commitear'). It names the alternatives but does not state when merging is preferable to alternatives like continue or handoff.

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 and does well: it discloses the reporter-role worker generation path, the default papercraft style, the fallback renderer on failure, and the return value (HTML path). It omits permissions, overwrite behavior, and error semantics, keeping it short of a 5.

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?

Three short sentences with the purpose front-loaded, then execution behavior, then return value. No filler, though the compressed '(ronda final)' aside slightly reduces readability.

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?

It correctly covers the return value in the absence of an output schema and explains the fallback path. It still leaves three undocumented parameters and no permission/error context for a 5-parameter tool, so it is adequate but 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 coverage is only 40% (open and style documented; title, subtitle, job_ids bare), so the description must compensate. It surfaces the real default style name 'papercraft' (the schema only references plugins.report.default_style) and ties inputs to 'jobs indicados', but adds nothing for open, title, or subtitle.

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: generating a pretty HTML report of what the listed jobs achieved. 'Jobs indicados (ronda final)' scopes it clearly enough to separate it from summarize/result, though it never names a sibling explicitly.

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 parenthetical '(ronda final)' implies this is meant to run after a final round of jobs, giving implicit timing guidance. However, there is no explicit when-to-use/when-not or routing against siblings like summarize or result.

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 discloses only the output shape. It says nothing about read-only vs mutating behavior, whether the job must be in a terminal state, latency, or error cases — significant gaps for a job-result tool.

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 compact sentence front-loads the output sections, with no filler. It is terse to the point of omitting the verb, but it is not bloated.

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?

No output schema exists, so the description must carry return-value meaning; it partially does by naming the sections, but omits the action it performs, the meaning of job_id, and the detail-level tradeoffs. For a job-scoped retrieval tool this is under-specified.

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 50%: 'detail' has an inline enum description, but 'job_id' is undocumented in both schema and description. The description never mentions either parameter or the detail levels, so it does not compensate for the coverage 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 names the output sections (RESULT/FILES/TESTS/RISKS), touched files and branch, which hints at a job-result retrieval tool, but it never states the verb or resource explicitly — no 'get/retrieve the result of a job'. It also does not distinguish itself from close siblings like report, status, or summarize.

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 indication of when to use this tool versus report, status, summarize, compact, or review, and no prerequisites (e.g., whether the job must be finished). The agent must infer usage entirely from the tool name.

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 does disclose the read-only nature ('solo lectura'), which is useful, but says nothing about whether the job must be running, which changes are examined (working tree vs. committed), permissions, or what the review returns.

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 short sentence with the read-only constraint and the two target scopes front-loaded; no filler. It is efficient, though the brevity is partly under-specification rather than true economy.

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 three undocumented parameters, no annotations, no output schema, and many overlapping siblings (diff, report, status, result), the description is too thin. An agent lacks the information needed to pick this tool or to invoke focus 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 coverage is 0% for all three parameters. The description implicitly maps 'job' to job_id and 'cwd' to cwd, but adds no format or semantics for them, and the 'focus' parameter is entirely undocumented in both the schema and the description.

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: a read-only review of the changes produced by a job or a cwd. That is clear enough to act on, but it never distinguishes itself from close siblings such as diff, report, or status, so an agent must guess which is the right one for examining changes.

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 by the scope 'changes of a job (or a cwd)' – it tells the agent what the tool operates on, not when to prefer it over diff, report, or status. No prerequisites, exclusions, or alternative-selection guidance are given.

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 it does disclose key traits: the agent runs without approvals and with internet access, returns a job_id, and can block up to timeout_s. It omits the side-effect profile (file edits), permission/auth requirements, and concurrency or budget behavior, so substantial gaps remain for a spawning tool.

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 dense sentences, front-loaded with the core action and followed by the return/wait contract. Every clause carries information; nothing is padded, though the parenthetical 'sin aprobaciones, con internet' could be slightly tighter.

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 9-param async job-spawning tool with no output schema, no annotations, and 16 siblings, the definition covers the basics (what it launches, job_id, blocking) but leaves routing decisions and the output contract unaddressed, so an agent could easily pick the wrong sibling or misuse wait/timeout combinations.

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 78%, just under the high-coverage baseline, and the description usefully compensates for the two undocumented params: wait (blocks for the report) and timeout_s (upper bound on the wait). It also clarifies the worker dependency (Codex vs OpenCode) that governs the worker param.

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 concrete verb and resource: it launches a worker agent (Codex/OpenCode depending on the worker), so the agent knows this spawns an autonomous job rather than running inline. It is clear despite the generic name 'run', but it never names how it differs from close siblings like run_many, continue, or handoff.

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 explicit when-to-use guidance and no alternatives named. The only implied usage cue is 'con wait=true espera el reporte', which tells the agent how to block, not when this tool should be preferred over run_many or continue.

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 does disclose one genuinely useful behavioral trait — simultaneous execution capped at COLMENA_MAX_PARALLEL with overflow queued — but says nothing about whether the call blocks, what it returns (job ids?), or how partial failures are reported.

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 sentence with zero waste; the parallelism behavior and the queueing constraint are both front-loaded. Nothing needs trimming.

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 an orchestrator that spawns up to 20 nested agent tasks, with no annotations and no output schema, the description is too thin: it omits return values, blocking behavior, failure semantics, and any pointer to the status/result/merge siblings needed to follow up on launched jobs.

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 reported at 0% for the top-level 'tasks' parameter, and the description adds no parameter meaning at all: it does not mention the array shape, the 1-20 item bounds, or the nested task/isolation/worker fields. The nested schema properties are individually documented, but the description itself compensates for none of the 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?

States a specific verb and resource: it launches several agents in parallel. The phrase 'varios ... en paralelo' implicitly contrasts with the singular sibling 'run', so an agent can distinguish batch from single-agent execution without opening the schema.

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 implied — batch execution is for multiple independent tasks — but the description never names the alternative ('run' for a single agent) or states when to prefer one over the other. No prerequisites or exclusions are given.

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 and no output schema, so the description carries the full burden – and it says nothing about whether this polls, blocks, returns terminal states, or what an unknown/expired job_id yields. Four words cannot satisfy that burden.

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?

Extremely short and front-loaded; nothing is wasted. It loses a point only because the brevity is under-specification rather than disciplined compression.

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?

A single-param tool is simple, but with no annotations, no output schema, no parameter docs, and no sibling differentiation, the definition leaves everything an agent needs unanswered – especially the distinction from 'result' and 'wait'.

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 0% and the single parameter 'job_id' has no description anywhere. The description mentions 'un job' but adds no format, origin, or validity information for job_id.

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 the resource ('job') and the returned concept ('estado'), so the purpose is discernible. But it names no specific verb beyond the implicit 'get', and gives no differentiation from siblings like result, wait, or list. Adequate but vague.

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 guidance at all on when to use this versus 'result' (get job output) or 'wait' (block until completion). With 17 siblings and several job-related ones, the absence of any routing guidance is a real gap.

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, and it discloses almost nothing. The aside '(rol summarizer)' hints that an LLM agent performs the work — implying nondeterminism, cost, and latency — but it never states whether the operation is read-only, whether it mutates job state, how long it takes, or whether output is persisted.

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?

It is a single short sentence with no filler and the action is front-loaded, which is structurally sound. However, the brevity comes from under-specification rather than tight editing, and the mixed-language framing ('Un agente...') spends words on implementation detail instead of 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?

With no annotations, no output schema, and 0% parameter description coverage, the description is the only source of information and it leaves the tool largely opaque. An agent cannot determine prerequisites, scope of the summary, or what 'focus' narrows without trial and error.

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, and it does not. It never explains what job_id identifies or what the optional 'focus' string does — arguably the most important thing to know about a summarization tool, since focus would steer the summary.

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 verb and resource ('resume la sesión de un job'), so the basic action is identifiable, but the phrasing 'Un agente (rol summarizer) resume...' describes the implementing mechanism rather than the tool's contract. It gives no way to tell it apart from siblings such as report, review, compact, or result, which all plausibly touch a job's session output.

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 guidance, no prerequisite (e.g. must the job be finished?), and no mention of alternatives despite a crowded sibling set (report, review, result, status). Usage is only implied by the verb 'resume'.

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. It does disclose the blocking nature and the 600 s ceiling, which is real behavioral value, but says nothing about what happens on timeout, whether the wait is interruptible, or error 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?

A single sentence with no filler; the action, scope, and limit are all front-loaded before the return-value clause.

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?

Three parameters, no output schema, and no annotations. The description covers the wait semantics and the timeout cap but leaves timeout defaults, return-report structure, and failure behavior unspecified.

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 partially does: 'uno o todos' maps to the any/all enum, and 'máx 600 s' documents the timeout_s ceiling, though the schema lacks the default and units for timeout_s and never clarifies job_ids semantics.

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 (wait) and resource (jobs), plus scope (one or all) and a hard cap (max 600 s). It does not differentiate itself from neighboring tools such as status or result, which an agent could easily confuse with waiting on a job.

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 guidance on when to prefer waiting over polling status, reading result, or cancelling. The 'one or all' phrasing hints at the mode parameter but never states the condition under which each is appropriate.

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, and it does disclose the returned fields (priority, strengths, monthly spend, remaining budget, availability). The read-only nature is implied by 'Lista', but nothing is said about auth needs or side effects beyond that.

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, zero filler: the resource and its contents come first, the usage cue second. Every clause earns its place and nothing is buried.

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 read tool with no output schema and no annotations, the description covers the essential return content an agent needs. It is complete enough to call correctly, with only minor gaps around the exact output shape.

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 no parameter semantics to explain and the baseline is 4. The description correctly adds no misleading parameter detail.

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 ('Lista los workers de colmena.yml') and enumerates what each entry contains (priority, strengths, spend, budget, availability). It is clearly distinguishable from generic siblings like 'list' or 'status', though it never names them explicitly to sharpen the contrast.

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?

'Úsalo para decidir a quién delegar' gives a clear use context, but there are no exclusions and no reference to alternative siblings (e.g. 'status', 'list', 'result') that an agent might otherwise pick. Usage is implied rather than fully guided.

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