Apolo

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

The annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful context beyond them by spelling out what information is returned, especially the app-vs-extension origin and the specific engines carried.

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 compact sentence that front-loads the version/origin/engines content, followed by a short usage cue. Every phrase earns its place, including the engine list, which tells the agent exactly what diagnostic detail is available.

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-only info tool with no output schema, the description is complete enough: it explains what is reported and when to call it. A little more on output shape could help, but the key facts are present.

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 the baseline is 4. Nothing about parameter semantics is missing or misleading.

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 purpose: reporting the version, the launch origin (app vs. Claude Desktop extension), and the bundled engines (libwebp, MozJPEG, oxipng, avifenc, cjxl). This is clearly distinguishable from the sibling optimization tools, though it doesn't explicitly contrast itself with them.

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 gives a clear usage trigger: "when someone asks about the version or something doesn't match what was expected." That covers the main diagnostic case, but it doesn't state when not to use it or name an alternative sibling.

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

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive behavior, so the safety profile is covered. The description adds useful boundaries beyond them: it works on both images and folders, and it deliberately does not evaluate quality. It stops short of describing output structure or failure modes, which keeps it at 4 rather than 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?

The tool's identity is stated first, followed by the usage rule, the exclusion, and a copy-pasteable example — an effective order with no filler. The opening noun phrase is slightly fragmented, and the example uses a field name the agent must map back to the schema.

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?

There is no output schema, but the parenthetical lists the returned attributes, which largely substitutes for one. With a single required parameter and rich annotations, nothing critical is missing, though it does not mention what a folder result looks like or how errors (bad path, non-image) surface.

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?

With only one parameter at 100% schema coverage, the schema already carries full meaning, so the baseline is a 4. The description adds a concrete example value showing an expanded tilde path to an image file, reinforcing that folders are also acceptable.

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 set of noun details it returns (format, dimensions, size, transparency, metadata, EXIF orientation) and also covers the folder-listing case, so the agent knows exactly what resource is inspected. It explicitly differentiates itself from the quality-measuring sibling.

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 gives an explicit ordering rule ('Use it first if you don't know what it is') and names the alternative for a different job ('It doesn't measure quality: for that, medir_calidad'). The when-to-use and when-to-use-something-else are both spelled out.

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

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

Annotations already declare non-read-only, non-destructive, idempotent, so the safety profile is covered. The description adds genuinely new behavioral context — "what has already been converted stays" — telling the agent this is a partial rollback rather than a full purge. It stops short of saying what happens to queued, unconverted items.

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, front-loaded fragments with no filler; the effect statement and the example each carry weight. It is arguably a touch under-specified rather than wordy.

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 mutation with no output schema, the key missing piece is the status of the unfinished portion of the batch and any error condition (unknown id, already-completed batch). Annotations cover safety, but the description leaves an agent guessing about post-cancel state.

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 explains that the id comes from empezar_lote with the “l-3” format. The inline example {"id": "l-1"} restates that format rather than adding new meaning, so 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?

"Stops a batch" names a specific verb and resource, and the partial-effect note makes clear what cancellation means here. It is distinguishable from empezar_lote and ver_lote by verb alone, though it never names them.

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 infers you call this to stop a running batch. There is no explicit when-to-use, no mention of empezar_lote (which produces the id) or ver_lote as an alternative for inspection, and no statement about what happens if the batch already finished.

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

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the write-but-not-destructive profile is structured data. The description adds genuinely new context: runtime cost (about 7 trials per format, over a minute at 12 MP, ~3 minutes at 24 MP) and the timeout risk that motivates empezar_lote. It does not disclose output file naming, where the comparison report goes, or what happens when no format reaches the target score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then saving behavior, then cost, then alternatives, then an example — every sentence carries information an agent needs to decide or call. No filler or restatement of the title.

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 12-parameter, nested-object tool with no output schema, the description covers what it returns at a high level (which format is lightest) and the side effects (new files, save all/none/best). What it omits — file naming, the report structure, and no-format-reaches-target behavior — are real but secondary gaps that the rich schema partly absorbs.

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 each parameter already carries a description with defaults and mutual exclusions, so the baseline is 3. The description only restates two defaults (80 score, the guardar modes) that the schema already documents, plus a call example that shows the ruta/formatos shape but adds no syntax 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?

States a specific verb chain (encode the same image in several formats at equal perceived quality, then pick the lightest) and names the comparison metric (SSIMULACRA 2). It also draws the boundary against siblings empezar_lote and optimizar_imagen, so the agent can select it 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?

Explicit routing: use empezar_lote with mas_ligero for images over ~20 MP because this tool can be cut off by a timeout, and use optimizar_imagen when a single output format is already decided. Both the when and the when-not are stated with the condition that selects the alternative.

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

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false; the description adds real context on top: asynchronous fire-and-return with an id, never overwriting existing files, default output naming, and serial execution. It doesn't cover failure handling or how cancellation interacts with cancelar_lote, so it's strong rather than complete.

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?

Front-loaded with the core action and return semantics, and every clause carries information (defaults, output location, sequencing). The long parenthetical sentence about default folders is dense and slightly run-on, which keeps it from a 5.

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 16-parameter asynchronous mutation with no output schema, the description covers the return contract (an id) and the next tool to call, plus the defaults an agent needs to omit parameters safely. Only error/progress behaviour is left 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?

Schema coverage is 100%, so the baseline is 3, but the description earns more by adding default behaviour not in the schema (WebP at score 80, photos-webp / photos-apolo folder naming) and a concrete example combining entradas, formatos and mas_ligero.

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: converts folders or many images in the background, subfolders included, returning an id immediately. That cleanly separates it from optimizar_imagen (single image) and ver_lote (polling the result).

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 names the follow-up step explicitly ("Afterwards, ver_lote") and says "one at a time", which tells the agent batches are serialized. It doesn't say when to prefer optimizar_imagen over a one-item batch, but the batch/single split is strongly implied.

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?

Goes meaningfully beyond the annotations: annotations only say readOnly=false, idempotent=false, destructive=false, while the description explains the exact failure mode (duplicate name = error), that nothing is overwritten, and that edits/deletes must happen in Apolo. This is the behavioral detail an agent needs before calling a non-idempotent write 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?

Three short sentences, front-loaded with the core action, followed by the constraint and then the example. The example earns its place as a usage anchor for a 14-parameter tool, though it is the least essential element.

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 14-parameter, non-idempotent creation tool with no output schema, the key facts (create-only, duplicate = error, where presets are edited) are all present and per-parameter meaning is fully covered by the schema. The only gap is that it never says what a successful call returns, which matters given there is no output schema.

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 baseline is 3; the description adds value by framing the input as a "combination of format and options" and giving a concrete worked example with nombre, formato, nota_objetivo and ancho. It doesn't explain precedence between `preset` and the overrides, but the schema already does that per-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+resource ("Saves a combination of format and options as a new preset") and adds the scope where the preset is usable (Apolo, command line, here). It also distinguishes itself from the absent mutating operations by saying changing or deleting presets is done in Apolo, so an agent knows this tool only 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?

The create-only condition is explicit ("if the name exists, it's an error"), which tells the agent when this tool will fail. It doesn't name a sibling for checking existing names, though the `preset` parameter description points to listar_presets, so the alternative path is inferable rather than stated up front.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety needs no repetition. The description adds genuine context beyond them: the list mirrors the app and CLI state, and each entry carries a format and a command. It does not describe ordering or empty-list behavior, but with no output schema the return content is at least characterized.

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 short sentences with zero filler: the first identifies the resource and its payload, the second names the consuming tools. The most actionable information, what the entries contain, is front-loaded.

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-only list tool with rich annotations, this covers what it returns and why an agent would call it. The only gap is the exact shape of each preset entry (field names, ordering), which no output schema documents either.

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 and the baseline applies. The mention of the `preset` field belongs to the sibling tools, not this one's inputs, so it does not add parameter semantics here.

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 (list) and resource (Apolo's saved presets) and adds what each entry contains: format and command. It also anchors the data to the same presets as the app and CLI. It does not explicitly name the write-side sibling guardar_preset, so the create-vs-read contrast is only implied.

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 tells the agent where the results are consumed: the `preset` parameter of optimizar_imagen and empezar_lote. That gives a clear call-before-optimizing workflow. It stops short of stating when not to use it or what happens if no presets exist.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds non-obvious behavioral context beyond them: the same-size requirement and the auto-rotation coupling ('if the result is auto-rotated, the original is auto-rotated too'). It doesn't describe the shape of the returned scores, which keeps it at 4.

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 core purpose and the metric scale are front-loaded, and each subsequent sentence (size constraint, rotation note, alternative tool, example) earns its place. It is slightly dense with parenthetical scale values 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?

For a read-only, two-parameter tool with no output schema, the description covers purpose, constraints, and metric names, which is nearly everything an agent needs. The only gap is that the return structure of the metrics isn't described, though the metric names partly imply it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already fully documented, making 3 the baseline. The description reinforces the constraint that original/resultado must match in size and supplies a concrete example payload, which adds modest value but no syntax beyond what the schema states.

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-like framing ('How far an image is from its original') and names the exact metrics produced (SSIMULACRA 2, PSNR, SSIM), so the resource and operation are unambiguous. It does not explicitly contrast itself with siblings like comparar_formatos or analizar_imagen, which keeps it below a 5.

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 gives a clear precondition ('They have to be the same size') and routes the agent to an alternative when the goal changes: 'To see where the loss is, ver_imagen with diferencias_con.' That is real when-to-use-this-vs-that guidance, though it lacks an explicit 'do not use for X' exclusion.

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?

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false) by disclosing that nothing is overwritten and collisions get -2, -3 suffixes, that omitting quality triggers an SSIMULACRA 2 search (costing a few seconds), and that processing happens against the user's local files with official engines. This makes the non-idempotent, non-destructive write semantics concrete.

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?

Dense but front-loaded: purpose, then default behavior, then sibling routing, then examples, then environment caveats. Every sentence carries information, though the examples block and the 'official engines' justification could be trimmed without loss.

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 16-parameter tool with no output schema, the description still explains the primary return ('gives the equivalent command for cwebp, cjpeg, oxipng, avifenc or cjxl') and the default decision path. It does not explicitly state whether the created file's path is returned, which is the one thing an agent might still need to discover.

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 baseline is 3; the description adds real value on top by stating the default target score of 80 when no quality is given, the default format (webp), and showing three concrete parameter combinations. The examples are illustrative rather than explaining every optional parameter, which the schema already handles.

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+resource ('Optimizes an image and saves it as a NEW file') with output-location and collision-naming behavior spelled out. It explicitly distinguishes itself from sibling workflows for format choice and batching, so an agent can place it immediately.

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?

Names the alternatives with their selecting conditions ('To choose between formats, comparar_formatos; for many images, empezar_lote') and adds a strong negative rule: don't convert images yourself in a cloud interpreter, use this so the file stays on the user's disk with the official engines. It even covers the edge case of images attached to the conversation, telling the agent to ask for a path.

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

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds the non-obvious behavioral fact that every view spends context budget, and reveals the default downscale (768 px) and that a difference map replaces the image output when diferencias_con is set. It stops short of describing returned image format or size interaction between lado_max and zona.

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?

Front-loaded with what the tool returns and its three modes, then the cost caveat, then compact examples. No filler sentences; every clause either defines a mode or constrains usage.

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 5-parameter tool with a nested object and no output schema, the description covers all modes and the interaction between them well enough to call it correctly. Minor gap: it does not clarify what happens if zona exceeds the image bounds or how lado_max is ignored when zona is given.

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 baseline is 3. The description goes beyond the schema by showing three concrete call shapes that demonstrate how ruta, diferencias_con, and the nested zona object combine, making the mutual interaction of these parameters explicit rather than leaving the agent to infer it.

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 concrete verb and resource: it returns the image for viewing, with the three distinct modes spelled out (scaled-down view, 1:1 area crop, difference map against an original). An agent understands exactly what comes back. It does not name or contrast with siblings like analizar_imagen or comparar_formatos, so it falls short of a 5.

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?

"Ask for one only when it helps" plus the note that each view consumes context gives a real usage condition and cost trade-off. The worked examples map each mode to a call shape. However, there is no explicit guidance on when to prefer this over analizar_imagen, comparar_formatos, or medir_calidad, which is the main selection risk given those 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?

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description still adds real behavior: it returns only images newer than "desde", emits a final summary when the batch ends, and blocks up to 25 seconds. That long-poll semantics are exactly what an agent needs to avoid a polling loop and is not in the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences plus one concrete example object, with the return shape front-loaded and the long-poll rule immediately after. Nothing is padded and the example disambiguates the call format.

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?

There is no output schema, so the description carries the burden of describing the return, which it does at the level of 'new images since desde' and 'summary when it ends', though it never names the response fields (e.g. siguiente_desde is only mentioned inside the parameter schema). For a read-only polling tool this is largely sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already defines id, desde, and esperar_segundos in detail. The description reinforces the coordination semantics (desde as a continuation cursor from the previous answer) and supplies a worked example, but adds little that the schema does not already say.

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 precisely what the tool returns: the batch's progress, the new images since "desde", and a closing summary. It doesn't explicitly name its siblings (empezar_lote, cancelar_lote), but the id parameter's origin already establishes it as the companion reader to empezar_lote.

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 gives clear guidance on the long-poll pattern: use esperar_segundos (max 25) to wait rather than re-asking in a loop. The condition for choosing a wait versus an immediate read is stated, though there is no explicit statement of when not to use the tool.

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