mcp-perception

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

With no annotations, the description carries the full burden. It discloses the report's contents (trust score, proofs, etc.) but does not mention behavioral aspects such as read-only nature, authorization requirements, potential errors (e.g., unknown agent), or whether the report is generated on-demand. The verb 'Returns' implies a read operation, but more explicit transparency would be helpful.

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 a single, well-structured sentence that front-loads the main action ('Returns a full EU AI Act compliance report') and then enumerates key contents. Every word contributes value, with no fluff or repetition.

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 simple one-parameter getter with no output schema, the description is fairly complete: it states the purpose, lists report components, and is supported by complete schema parameter documentation. However, it could additionally mention the absence of real-time guarantees or clarify what 'regulatory status' entails, leaving a small gap.

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

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

The input schema has one parameter 'agentHandle' with a full description ('GNS handle of the agent (e.g. energy@italy-geiant)'), so schema coverage is 100%. The tool description does not add parameter details, but the schema already provides sufficient meaning. Baseline of 3 is appropriate since no additional semantic value is needed.

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 uses the specific verb 'Returns' and identifies the resource as a 'full EU AI Act compliance report for a GNS agent', listing concrete components (trust score, chain verification, Merkle epoch proofs, delegation certificate, regulatory status). This clearly distinguishes it from siblings like gns_get_trust_score and gns_verify_chain, which focus on individual aspects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool provides a comprehensive report, but it does not explicitly state when to choose it over narrower siblings. For example, it lacks guidance like 'use gns_get_trust_score for just the trust score'. The presence of siblings suggests alternatives, but the description offers no direct comparison or exclusions.

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

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

With no annotations provided, the description carries the full burden of explaining behavior. It discloses the possible output tiers and percentages, and clarifies the meaning of omitting agent_pk. This adds valuable context about what the tool returns and how input affects behavior, though it doesn't explicitly state read-only status or error handling.

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 two sentences: the first is a clear purpose statement, the second adds the tier scale and a usage tip. It is front-loaded, concise, and every sentence contributes meaningful information without redundancy.

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

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

For a simple tool with one optional parameter and no output schema, the description covers the core purpose, the range of possible return values (tiers and percentages), and the key input behavior. It could specify the exact return format or error conditions, but for this simplicity it is largely complete.

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 input schema has 100% description coverage for agent_pk, including its format and omission behavior. The tool description repeats the omission instruction but adds no new parameter-level meaning beyond what the schema already provides, so the baseline of 3 applies.

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

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

The description clearly states 'Get the current TierGate trust tier and score for an agent' with a specific verb and resource. It uniquely identifies the tool among siblings like 'gns_get_compliance_report' by focusing on trust tier/score, and even lists the tier progression to disambiguate further.

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 provides a clear usage instruction: 'Omit agent_pk to query the server's own agent.' This gives parameter-specific guidance and implies when the tool is appropriate (querying trust scores). However, it does not explicitly mention alternatives or when not to use it, so it falls short of a 5.

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

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

With no annotations provided, the description carries the full burden. It discloses that the operation 'seals' the epoch (implying finality/irreversibility), uses a Merkle root for tamper evidence, and returns a structured result. This goes beyond a simple 'rolls breadcrumbs' and gives meaningful behavioral context about the irreversible, compliance-oriented nature of the action.

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 two sentences, front-loaded with the primary action and result. Every sentence adds value: the first states the operation and output; the second specifies when to invoke it and why. There is no redundancy or filler.

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

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

Despite lacking an output schema and annotations, the description covers the essential aspects: what the tool does (rolls pending breadcrumbs into a sealed epoch), when to use it (end of session), what it returns (epoch_index, merkle_root, block_count, epoch_hash), and the broader purpose (tamper-evident compliance snapshot). This is sufficient for an agent to invoke it correctly without additional structured information.

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 has zero parameters, so the baseline is 4. The description effectively explains the scope via 'all pending breadcrumbs' and the return values, meaning there is no parameter ambiguity. No additional parameter documentation needed.

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 uses a specific verb 'Roll' with a clear resource: 'all pending breadcrumbs into a new sealed epoch with a Merkle root.' It clearly distinguishes from siblings like gns_get_compliance_report or gns_verify_chain by describing a state-changing operation that seals data. The return fields are explicit, reinforcing the purpose.

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 provides explicit guidance: 'Call this at the end of a session to produce a tamper-evident compliance snapshot.' This clearly indicates when to use the tool. It does not explicitly mention alternatives or when not to use it, but the context is distinct enough from sibling tools that usage intent is unambiguous.

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 provides useful behavioral detail: it lists the exact return shape ({ is_valid, block_count, issues[] } plus epoch Merkle roots) and explains the semantic meaning of a valid chain. It does not address permissions or side effects, but verification is inherently non-destructive and the return semantics add clarity.

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, front-loaded with the core action, and packed with necessary detail (return shape and guarantee). No wasted words.

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?

The tool has one optional parameter and no output schema; the description compensates by explaining the return fields and the validity guarantee. It is sufficient for selecting and invoking the tool, though it could be more explicit about when to prefer it over sibling verification-like tools.

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 parameter agent_pk is fully described in the schema as an Ed25519 public key with an omit-for-own-agent note. The description adds no additional parameter context, so the baseline of 3 is appropriate.

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

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

The description uses the specific verb 'Verify' with the resource 'an agent's breadcrumb chain' and states cryptographic integrity. It clearly distinguishes from sibling tools like gns_get_compliance_report and gns_get_trust_score by focusing on tamper-evidence verification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies this tool is for checking integrity of a breadcrumb chain, giving context for when it would be used. It does not explicitly name alternatives or exclusions, so it stops short of a 5.

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

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

With no annotations provided, the description carries the burden of disclosing side effects, and it does: it writes the perception chain to Spatial Memory and drops a signed audit breadcrumb. It also reveals that it sends data to a RunPod endpoint and lists the returned fields. However, it omits details about failure behavior, permissions, or whether the memory write can be disabled beyond the parameter default.

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 main action, and every sentence earns its place: what it does, what it returns, and what side effects it has. No filler or redundant restatement of the name.

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?

The description covers the essential prerequisites, processing location (RunPod), return fields, and side effects. Since there is no output schema, it reasonably enumerates the main return values, though it leaves the structure of 'perception_chain' unspecified and does not discuss error conditions. Still, it provides a solid operational picture for a moderately complex 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 description coverage is 100%, so the baseline is 3. The description adds no extra parameter-level meaning beyond the schema, but it reinforces that tile_id must come from a prior fetch and that the chain is written to memory. No compensation needed since the schema already documents each parameter's purpose.

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, actionable verb: "Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile." It clearly identifies the resource (Sentinel-2 tile), the operation (classification), and distinguishes it from siblings like perception_fetch_tile and perception_embed.

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 tool explicitly states it operates on a tile 'previously fetched by perception_fetch_tile', which establishes a required sequencing precondition. It does not explicitly enumerate when to avoid using it or name alternative tools for other tasks, but the prerequisite and domain are clearly 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?

With no annotations, the description carries the burden of behavioral disclosure. It transparently states the tool is 'NOT YET IMPLEMENTED', which is an important behavioral trait (calling it will likely fail or do nothing). However, it does not describe expected errors, safety, or any side effects, and the future tense is ambiguous for current behavior.

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

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

The description is a single, concise sentence that front-loads the critical 'NOT YET IMPLEMENTED' status. It is efficient, but it lacks substantive detail that might be expected even for a placeholder, so it doesn't earn 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?

Given the tool has one parameter, no output schema, and no annotations, the description is very incomplete. It provides no context about what embeddings are for, how they relate to perception_fetch_tile, or any use-case information. The 'NOT YET IMPLEMENTED' status explains its unavailability but does not help an agent understand the tool's intended role.

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 input schema already provides 100% coverage with a clear description for tile_id ('tile_id from perception_fetch_tile result'). The description adds no additional parameter semantics, so the baseline score of 3 applies.

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

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

The description states a future intent ('Will generate Clay v1.5 embeddings') but is not currently implemented, so it does not describe actual current functionality. The verb 'generate' and resource 'embeddings' provide some specific purpose, but the explicit 'NOT YET IMPLEMENTED' makes it vague as a description of a usable 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?

There is no guidance on when to use this tool or how to choose it over siblings like perception_classify or perception_fetch_tile. The 'NOT YET IMPLEMENTED' label implies it should not be used, but there is no explicit direction or alternative suggested.

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

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

With no annotations provided, the description carries the full burden. It discloses the source, the return content (signed COG band URLs for six bands plus metadata), and the in-memory caching behavior. It does not mention authentication, rate limits, or URL expiration, but the core behavioral traits are covered.

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 concise sentences. The first sentence states the action and subject; the second lists the return value and the caching side effect. Every clause earns its place, and key information 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?

Although there is no output schema, the description explicitly enumerates the six spectral bands and notes the inclusion of tile metadata, which covers return values. It also mentions the caching behavior that links to sibling tools. A small gap is the absence of failure/edge-case behavior, but for a fetch tool with well-documented parameters, this is reasonably complete.

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 input schema already provides 100% parameter coverage with descriptions for h3_cell, days_back, timestamp, and max_cloud_cover. The tool description adds context about the tile selection ('least-cloudy') and cache usage, but does not add new parameter-level semantics, so the baseline of 3 applies.

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

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

The description clearly states the action ('Fetch'), the specific resource ('least-cloudy Sentinel-2 L2A tile covering a given H3 cell'), and the source ('Microsoft Planetary Computer'). It also distinguishes itself by enumerating the returned bands and noting the cache behavior for subsequent perception_classify or perception_embed calls.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool by noting the tile is cached for subsequent perception_classify or perception_embed calls, which gives contextual placement among siblings. It does not explicitly state when not to use it or name an alternative, but the guidance is sufficient for typical usage.

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 discloses a significant side effect: writing to Spatial Memory and dropping an audit breadcrumb. However, it states the write unconditionally, while the schema has a write_to_spatial_memory parameter that can disable it, creating a potential inaccuracy.

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 with no redundant phrasing. The verb 'Query' is front-loaded, and the sentence structure efficiently conveys purpose, return data, and side effects.

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

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

Given no output schema and no annotations, the description adequately lists the return fields (wind, precipitation, temperature) and side effects. However, it omits details about response format, units, or the optionality of the timestamp, which are only evident from the 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 description coverage is 100%, so the baseline is 3. The description adds little beyond the schema, except implying the timestamp and H3 cell are key inputs. It does not clarify the write_to_spatial_memory parameter's role, which is mentioned in the description but not linked to 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?

The description clearly states the tool queries atmospheric conditions for an H3 cell at a timestamp, listing specific return types (wind, precipitation, temperature) and the data source (Open-Meteo ERA5). This distinguishes it from sibling tools like perception_classify or perception_fetch_tile.

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 provides clear context for when to use the tool (query weather for a geospatial cell) but does not explicitly mention alternatives or exclusions. The context is sufficient without being explicit about when-not-to-use.

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