TinyPNG MCP by usefulapi

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

Annotations only mark this as a non-read-only, non-idempotent, open-world write; the description adds substantial context beyond them: resulting output_url is key-gated, Tinify retains the image ~48 hours, each call decrements a monthly quota (500 free), and resize/convert each cost an extra compression. That is rich operational disclosure.

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

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

It front-loads the most decision-relevant fact ('WRITE (uses quota)') then packs purpose, return shape, retention, and sibling routing into tight sentences with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and discharges it: output_url, compressed size and type, savings, and Compression-Count header. Quota, retention, and alternatives are all covered, so an agent can call this correctly without further lookup.

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 lone 'url' parameter is fully described there, including the internet-reachability requirement. The description restates that Tinify's servers fetch the URL but adds no syntax or formatting detail beyond the schema, so baseline 3 is correct.

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?

Names a specific write operation ('ask TinyPNG to fetch a public image by URL and compress it'), enumerates the supported formats, and distinguishes itself from siblings by delegating resizing/converting to tinypng_transform_image and byte retrieval to tinypng_download_image.

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: use tinypng_download_image for bytes and tinypng_transform_image for resize/convert/metadata. It also states the costs (quota consumption, extra compression per resize/convert), which is exactly the when-to-use-wisely guidance an agent needs.

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?

Beyond the readOnlyHint/destructiveHint annotations, the description discloses non-obvious traits: the ~48-hour output validity window, that images over 1 MB are described rather than returned inline, and that downloading consumes no extra compression quota. These are exactly the operational facts an agent needs before calling.

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-loads the action and the source of the input, then packs expiry, return shape, size threshold and quota into a compact block. Dense but every clause carries information; the trailing 'GET /output/{id}' is a useful endpoint anchor rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and one parameter, the description carries the burden well by describing the returned image and its metadata. The one wrinkle is the >1 MB case, where it says the image is 'described' without specifying what representation the caller actually receives.

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

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

Schema description coverage is 100%, so the sole parameter's format, length bounds and 48h note are already documented in the schema. The description restates the 48h validity but adds no new syntax or format detail beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Fetch the compressed image... and return it as an image') and ties it directly to the sibling that produces the input ('of an earlier tinypng_compress_image'). An agent can distinguish this from tinypng_compress_image and tinypng_transform_image without opening a 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?

Clearly states the condition for use: retrieving the output of a prior compress call via its output_url, within a ~48h window. It does not explicitly contrast against tinypng_transform_image or note what to do when the output has expired, so it falls short of full when/when-not guidance.

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

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

Annotations only cover the generic read-only/no-destruction profile; the description adds genuinely non-obvious behavior: the check issues an empty request that Tinify refuses so no image is compressed and no quota is consumed. It also names the underlying signal (Compression-Count header) and the endpoint used, which an agent could not infer from the schema.

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 sentences, front-loaded with the purpose and then the safety explanation before the plan comparison. Information density is high and every clause earns its place, though the parenthetical header name and endpoint spec make it slightly denser than strictly necessary.

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 output schema, the description carries the return-value burden and does so: it states that the result is the monthly compression count and key validity. Combined with the no-quota-consumed guarantee and the free-plan reference, an agent has everything needed to call and interpret this tool.

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

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

There are zero parameters and 100% schema coverage, so the baseline is 4. The description correctly signals the parameterless nature ('POST /shrink with no body'), confirming no input is expected beyond the configured API key.

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: reporting how many compressions the API key has used this calendar month plus key validity. This is clearly distinguishable from the sibling tools (compress, download, transform), none of which report quota or key state.

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 the context for using it — comparing consumption against the Tinify plan, with the free plan's 500/month figure — which implies a pre-flight quota check. It stops short of an explicit 'call this before compressing to avoid overage' instruction or any when-not clause, so it is clear context rather than full routing guidance.

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

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses quota cost per operation (resize and convert each cost one extra compression, preserve is free), the 48-hour validity window of outputs, the 1 MB cap on returned images, and the fact that Tinify returns bytes only with no new URL. These are material operational facts an agent cannot infer from 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?

The description is dense and front-loads the WRITE/quota warning, then proceeds method-by-method (Resize / Convert / Preserve), which is easy to scan. It is long for a tool description, and the include_image/1 MB rule is restated twice, which is a small 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?

There is no output schema, so the description carries the return-value burden and does so fully: resulting type, byte size, width, height, Compression-Count, plus the conditional image payload. It also covers expiry, quota, and the endpoint, leaving nothing essential unstated for an 8-parameter tool.

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

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

Schema coverage is already 100%, so the baseline is 3, but the description adds real semantic value: it explains the cross-parameter constraint that scale takes width OR height while fit/cover/thumb require both, that images are never scaled up, that multiple convert targets return the smallest result, and that transparent-to-JPEG conversion requires a background colour. This goes beyond the per-field schema 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?

Opens with a specific verb and resource ("WRITE (uses quota): apply a resize, a format conversion and/or metadata preservation to an image") and explicitly anchors the input to the sibling tool's output ("the output_url from tinypng_compress_image"). An agent can distinguish this from tinypng_compress_image without opening either 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?

Gives clear context for when to use it: it operates on an already-compressed image from tinypng_compress_image, within a ~48 hour window, and each call is a fresh request. It does not explicitly state when NOT to use it or point to tinypng_download_image as the alternative for fetching files, so it falls short of full routing guidance.

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